[PATCH bpf-next v3 10/13] selftests/bpf: Add C tests for 16-byte returns in R0:R2

[Yonghong Song <yonghong.song@linux.dev>]

Add selftests that exercise a 16-byte return value passed in the R0:R2
register pair, written in C so that they depend on the compiler lowering
the register-pair return. Covered are an __int128 return, a 16-byte struct
return (from a static and from a global subprogram) and a 16-byte union
return, plus __int128 and 16-byte struct returns from a kfunc, for which
bpf_kfunc_call_test_i128() and bpf_kfunc_call_test_ret_pair() are added to
bpf_testmod.

The R0:R2 convention is only emitted by LLVM 23 and newer. Each object
records in a read-only has_reg_pair_ret flag which compiler built it; where
that is false the programs are stubs and subtests report a skip rather than
a pass.

The two kfunc subtests further depend on the JIT: bpf_add_kfunc_call()
rejects a kfunc returning more than 8 bytes with -EOPNOTSUPP where
bpf_jit_supports_kfunc_ret_reg_pair() is false. Those calls therefore live
in an object of their own, and that load failing with -EOPNOTSUPP is what
turns the two subtests into skips, so no list of the JITs implementing the
pair needs to be kept here. A register-pair return from a BPF subprogram
needs no JIT support, so the remaining subtests run everywhere.

bpf_kfunc_call_test_i128() is guarded by __SIZEOF_INT128__, which the
compiler only defines on 64-bit targets. A return value in R0:R2 is
supported on 64-bit architectures only, so the guard is there to keep
bpf_testmod building on a 32-bit target, not to make the test run there.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
---
 .../selftests/bpf/prog_tests/aggregate_ret.c  | 122 ++++++++++++++++++
 .../bpf/progs/aggregate_ret_int128_c.c        |  48 +++++++
 .../bpf/progs/aggregate_ret_kfunc_c.c         |  66 ++++++++++
 .../bpf/progs/aggregate_ret_struct_c.c        |  82 ++++++++++++
 .../bpf/progs/aggregate_ret_union_c.c         |  58 +++++++++
 .../selftests/bpf/test_kmods/bpf_testmod.c    |  23 ++++
 .../bpf/test_kmods/bpf_testmod_kfunc.h        |  13 ++
 7 files changed, 412 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/aggregate_ret.c
 create mode 100644 tools/testing/selftests/bpf/progs/aggregate_ret_int128_c.c
 create mode 100644 tools/testing/selftests/bpf/progs/aggregate_ret_kfunc_c.c
 create mode 100644 tools/testing/selftests/bpf/progs/aggregate_ret_struct_c.c
 create mode 100644 tools/testing/selftests/bpf/progs/aggregate_ret_union_c.c

diff --git a/tools/testing/selftests/bpf/prog_tests/aggregate_ret.c b/tools/testing/selftests/bpf/prog_tests/aggregate_ret.c
new file mode 100644
index 000000000000..e4317399d711
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/aggregate_ret.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+#include "aggregate_ret_int128_c.skel.h"
+#include "aggregate_ret_struct_c.skel.h"
+#include "aggregate_ret_union_c.skel.h"
+#include "aggregate_ret_kfunc_c.skel.h"
+
+static void run_prog(struct bpf_program *prog, bool supported)
+{
+	char buf[64] = {};
+	int err, prog_fd;
+	LIBBPF_OPTS(bpf_test_run_opts, topts,
+		    .data_in = buf,
+		    .data_size_in = sizeof(buf),
+		    .repeat = 1,
+	);
+
+	if (!supported) {
+		test__skip();
+		return;
+	}
+
+	prog_fd = bpf_program__fd(prog);
+	err = bpf_prog_test_run_opts(prog_fd, &topts);
+	if (!ASSERT_OK(err, "test_run"))
+		return;
+
+	ASSERT_EQ(topts.retval, 0, "aggregate_ret_result");
+}
+
+static void test_int128_c(void)
+{
+	struct aggregate_ret_int128_c *skel;
+
+	skel = aggregate_ret_int128_c__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_int128_c_open_load"))
+		return;
+
+	if (test__start_subtest("int128_c"))
+		run_prog(skel->progs.aggregate_ret_int128_c_test,
+			 skel->rodata->has_reg_pair_ret);
+
+	aggregate_ret_int128_c__destroy(skel);
+}
+
+static void test_struct_c(void)
+{
+	struct aggregate_ret_struct_c *skel;
+
+	skel = aggregate_ret_struct_c__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_struct_c_open_load"))
+		return;
+
+	if (test__start_subtest("struct_c"))
+		run_prog(skel->progs.aggregate_ret_struct_c_test,
+			 skel->rodata->has_reg_pair_ret);
+
+	if (test__start_subtest("global_struct_c"))
+		run_prog(skel->progs.aggregate_ret_global_struct_c_test,
+			 skel->rodata->has_reg_pair_ret);
+
+	aggregate_ret_struct_c__destroy(skel);
+}
+
+static void test_union_c(void)
+{
+	struct aggregate_ret_union_c *skel;
+
+	skel = aggregate_ret_union_c__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_union_c_open_load"))
+		return;
+
+	if (test__start_subtest("union_c"))
+		run_prog(skel->progs.aggregate_ret_union_c_test,
+			 skel->rodata->has_reg_pair_ret);
+
+	aggregate_ret_union_c__destroy(skel);
+}
+
+static void test_kfunc_c(void)
+{
+	struct aggregate_ret_kfunc_c *skel;
+	bool supported;
+	int err;
+
+	skel = aggregate_ret_kfunc_c__open();
+	if (!ASSERT_OK_PTR(skel, "skel_kfunc_c_open"))
+		return;
+
+	supported = skel->rodata->has_reg_pair_ret;
+
+	/*
+	 * Where the JIT cannot hand the second half of a >8-byte kfunc return
+	 * back in R0:R2, bpf_add_kfunc_call() rejects the call with
+	 * -EOPNOTSUPP. Asking the kernel keeps this test free of a list of the
+	 * JITs that can, which would have to be updated as the rest of them
+	 * learn.
+	 */
+	err = aggregate_ret_kfunc_c__load(skel);
+	if (err == -EOPNOTSUPP)
+		supported = false;
+	else if (!ASSERT_OK(err, "skel_kfunc_c_load"))
+		goto out;
+
+	if (test__start_subtest("kfunc_int128_c"))
+		run_prog(skel->progs.aggregate_ret_kfunc_int128_c_test, supported);
+
+	if (test__start_subtest("kfunc_struct_c"))
+		run_prog(skel->progs.aggregate_ret_kfunc_struct_c_test, supported);
+
+out:
+	aggregate_ret_kfunc_c__destroy(skel);
+}
+
+void test_aggregate_ret(void)
+{
+	test_int128_c();
+	test_struct_c();
+	test_union_c();
+	test_kfunc_c();
+}
diff --git a/tools/testing/selftests/bpf/progs/aggregate_ret_int128_c.c b/tools/testing/selftests/bpf/progs/aggregate_ret_int128_c.c
new file mode 100644
index 000000000000..f2e09c8be0be
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/aggregate_ret_int128_c.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#if defined(__clang_major__) && __clang_major__ >= 23
+
+const volatile bool has_reg_pair_ret = true;
+
+#define MIX_A	0xdeadbeefcafef00dULL
+#define MIX_B	0x0123456789abcdefULL
+
+typedef unsigned __int128 u128;
+
+static __noinline u128 make_i128(__u64 a, __u64 b)
+{
+	return ((u128)(a + b) << 64) | (a - b);
+}
+
+SEC("tc")
+int aggregate_ret_int128_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	u128 v;
+
+	v = make_i128(a, b);
+	if ((__u64)(v >> 64) != a + b)
+		return 1;
+	if ((__u64)v != a - b)
+		return 2;
+
+	return 0;
+}
+
+#else
+
+const volatile bool has_reg_pair_ret = false;
+
+SEC("tc")
+int aggregate_ret_int128_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/aggregate_ret_kfunc_c.c b/tools/testing/selftests/bpf/progs/aggregate_ret_kfunc_c.c
new file mode 100644
index 000000000000..fd000620f314
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/aggregate_ret_kfunc_c.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include "../test_kmods/bpf_testmod_kfunc.h"
+
+#if defined(__clang_major__) && __clang_major__ >= 23
+
+const volatile bool has_reg_pair_ret = true;
+
+#define MIX_A	0xdeadbeefcafef00dULL
+#define MIX_B	0x0123456789abcdefULL
+
+typedef unsigned __int128 u128;
+
+SEC("tc")
+int aggregate_ret_kfunc_int128_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	u128 v;
+
+	v = bpf_kfunc_call_test_i128(a, b);
+	if ((__u64)(v >> 64) != a + b)
+		return 1;
+	if ((__u64)v != a - b)
+		return 2;
+
+	return 0;
+}
+
+SEC("tc")
+int aggregate_ret_kfunc_struct_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	struct prog_test_ret_pair p;
+
+	p = bpf_kfunc_call_test_ret_pair(a, b);
+	if (p.hi != a + b)
+		return 1;
+	if (p.lo != a - b)
+		return 2;
+
+	return 0;
+}
+
+#else
+
+const volatile bool has_reg_pair_ret = false;
+
+SEC("tc")
+int aggregate_ret_kfunc_int128_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+SEC("tc")
+int aggregate_ret_kfunc_struct_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/aggregate_ret_struct_c.c b/tools/testing/selftests/bpf/progs/aggregate_ret_struct_c.c
new file mode 100644
index 000000000000..5296e41da3f0
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/aggregate_ret_struct_c.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#if defined(__clang_major__) && __clang_major__ >= 23
+
+const volatile bool has_reg_pair_ret = true;
+
+#define MIX_A	0xdeadbeefcafef00dULL
+#define MIX_B	0x0123456789abcdefULL
+
+struct pair {
+	__u64 hi;	/* R0 */
+	__u64 lo;	/* R2 */
+};
+
+static __noinline struct pair make_pair(__u64 a, __u64 b)
+{
+	struct pair p = { .hi = a + b, .lo = a - b };
+
+	return p;
+}
+
+SEC("tc")
+int aggregate_ret_struct_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	struct pair p;
+
+	p = make_pair(a, b);
+	if (p.hi != a + b)
+		return 1;
+	if (p.lo != a - b)
+		return 2;
+
+	return 0;
+}
+
+__noinline struct pair make_pair_global(__u64 a, __u64 b)
+{
+	struct pair p = { .hi = a + b, .lo = a - b };
+
+	return p;
+}
+
+SEC("tc")
+int aggregate_ret_global_struct_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	struct pair p;
+
+	p = make_pair_global(a, b);
+	if (p.hi != a + b)
+		return 1;
+	if (p.lo != a - b)
+		return 2;
+
+	return 0;
+}
+
+#else
+
+const volatile bool has_reg_pair_ret = false;
+
+SEC("tc")
+int aggregate_ret_struct_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+SEC("tc")
+int aggregate_ret_global_struct_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/aggregate_ret_union_c.c b/tools/testing/selftests/bpf/progs/aggregate_ret_union_c.c
new file mode 100644
index 000000000000..5547fa6cbd49
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/aggregate_ret_union_c.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2026 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+#if defined(__clang_major__) && __clang_major__ >= 23
+
+const volatile bool has_reg_pair_ret = true;
+
+#define MIX_A	0xdeadbeefcafef00dULL
+#define MIX_B	0x0123456789abcdefULL
+
+union pair {
+	__u64 halves[2];
+	struct {
+		__u64 lo;	/* R0 */
+		__u64 hi;	/* R2 */
+	} parts;
+};
+
+static __noinline union pair make_pair(__u64 a, __u64 b)
+{
+	union pair p;
+
+	p.halves[0] = a + b;
+	p.halves[1] = a - b;
+	return p;
+}
+
+SEC("tc")
+int aggregate_ret_union_c_test(struct __sk_buff *skb)
+{
+	__u64 a = skb->len ^ MIX_A;
+	__u64 b = skb->len ^ MIX_B;
+	union pair p;
+
+	p = make_pair(a, b);
+	if (p.parts.lo != a + b)
+		return 1;
+	if (p.parts.hi != a - b)
+		return 2;
+
+	return 0;
+}
+
+#else
+
+const volatile bool has_reg_pair_ret = false;
+
+SEC("tc")
+int aggregate_ret_union_c_test(struct __sk_buff *skb)
+{
+	return 0;
+}
+
+#endif
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
index a6133f7521f3..1c26905cec41 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c
@@ -939,6 +939,25 @@ __bpf_kfunc int bpf_kfunc_call_test5(u8 a, u16 b, u32 c)
 	return 0;
 }
 
+/*
+ * A 16-byte return value in R0:R2 is only supported on 64-bit architectures,
+ * which are also the only ones where the compiler defines __SIZEOF_INT128__.
+ * Guard the kfunc so that the module still builds on a 32-bit target.
+ */
+#ifdef __SIZEOF_INT128__
+__bpf_kfunc __int128 bpf_kfunc_call_test_i128(u64 a, u64 b)
+{
+	return (__int128)(((unsigned __int128)(a + b) << 64) | (a - b));
+}
+#endif
+
+__bpf_kfunc struct prog_test_ret_pair bpf_kfunc_call_test_ret_pair(u64 a, u64 b)
+{
+	struct prog_test_ret_pair r = { .hi = a + b, .lo = a - b };
+
+	return r;
+}
+
 __bpf_kfunc u64 bpf_kfunc_call_stack_arg(u64 a, u64 b, u64 c, u64 d,
 					 u64 e, u64 f, u64 g, u64 h,
 					 u64 i, u64 j)
@@ -1472,6 +1491,10 @@ BTF_ID_FLAGS(func, bpf_kfunc_call_test2)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test3)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test4)
 BTF_ID_FLAGS(func, bpf_kfunc_call_test5)
+#ifdef __SIZEOF_INT128__
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_i128)
+#endif
+BTF_ID_FLAGS(func, bpf_kfunc_call_test_ret_pair)
 BTF_ID_FLAGS(func, bpf_kfunc_call_stack_arg)
 BTF_ID_FLAGS(func, bpf_kfunc_call_stack_arg_ptr)
 BTF_ID_FLAGS(func, bpf_kfunc_call_stack_arg_mix)
diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
index c4383acb53c1..b190917f36b8 100644
--- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
+++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod_kfunc.h
@@ -55,6 +55,15 @@ struct prog_test_big_arg {
 	__u64 b;
 };
 
+/*
+ * A 16-byte struct returned by value from a kfunc: .hi comes back in R0 and
+ * .lo in R2.
+ */
+struct prog_test_ret_pair {
+	__u64 hi;
+	__u64 lo;
+};
+
 struct prog_test_fail1 {
 	void *p;
 	int x;
@@ -130,6 +139,10 @@ int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
 struct sock *bpf_kfunc_call_test3(struct sock *sk) __ksym;
 long bpf_kfunc_call_test4(signed char a, short b, int c, long d) __ksym;
 int bpf_kfunc_call_test5(__u8 a, __u16 b, __u32 c) __ksym;
+#ifdef __SIZEOF_INT128__
+__int128 bpf_kfunc_call_test_i128(__u64 a, __u64 b) __ksym;
+#endif
+struct prog_test_ret_pair bpf_kfunc_call_test_ret_pair(__u64 a, __u64 b) __ksym;
 __u64 bpf_kfunc_call_stack_arg(__u64 a, __u64 b, __u64 c, __u64 d,
 			       __u64 e, __u64 f, __u64 g, __u64 h,
 			       __u64 i, __u64 j) __ksym;
-- 
2.53.0-Meta