Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Alexei Starovoitov says:

====================
pull-request: bpf-next 2021-11-01

We've added 181 non-merge commits during the last 28 day(s) which contain
a total of 280 files changed, 11791 insertions(+), 5879 deletions(-).

The main changes are:

1) Fix bpf verifier propagation of 64-bit bounds, from Alexei.

2) Parallelize bpf test_progs, from Yucong and Andrii.

3) Deprecate various libbpf apis including af_xdp, from Andrii, Hengqi, Magnus.

4) Improve bpf selftests on s390, from Ilya.

5) bloomfilter bpf map type, from Joanne.

6) Big improvements to JIT tests especially on Mips, from Johan.

7) Support kernel module function calls from bpf, from Kumar.

8) Support typeless and weak ksym in light skeleton, from Kumar.

9) Disallow unprivileged bpf by default, from Pawan.

10) BTF_KIND_DECL_TAG support, from Yonghong.

11) Various bpftool cleanups, from Quentin.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (181 commits)
  libbpf: Deprecate AF_XDP support
  kbuild: Unify options for BTF generation for vmlinux and modules
  selftests/bpf: Add a testcase for 64-bit bounds propagation issue.
  bpf: Fix propagation of signed bounds from 64-bit min/max into 32-bit.
  bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and var_off.
  selftests/bpf: Fix also no-alu32 strobemeta selftest
  bpf: Add missing map_delete_elem method to bloom filter map
  selftests/bpf: Add bloom map success test for userspace calls
  bpf: Add alignment padding for "map_extra" + consolidate holes
  bpf: Bloom filter map naming fixups
  selftests/bpf: Add test cases for struct_ops prog
  bpf: Add dummy BPF STRUCT_OPS for test purpose
  bpf: Factor out helpers for ctx access checking
  bpf: Factor out a helper to prepare trampoline for struct_ops prog
  selftests, bpf: Fix broken riscv build
  riscv, libbpf: Add RISC-V (RV64) support to bpf_tracing.h
  tools, build: Add RISC-V to HOSTARCH parsing
  riscv, bpf: Increase the maximum number of iterations
  selftests, bpf: Add one test for sockmap with strparser
  selftests, bpf: Fix test_txmsg_ingress_parser error
  ...
====================

Link: https://lore.kernel.org/r/20211102013123.9005-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

75 files changed, 1257 insertions, 359 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index ba0e1efe5a45..0f9525293881 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -4,13 +4,13 @@
 
 #include "atomics.lskel.h"
 
-static void test_add(struct atomics *skel)
+static void test_add(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__add__attach(skel);
+	link_fd = atomics_lskel__add__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(add)"))
 		return;
 
@@ -36,13 +36,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_sub(struct atomics *skel)
+static void test_sub(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__sub__attach(skel);
+	link_fd = atomics_lskel__sub__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(sub)"))
 		return;
 
@@ -69,13 +69,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_and(struct atomics *skel)
+static void test_and(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__and__attach(skel);
+	link_fd = atomics_lskel__and__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(and)"))
 		return;
 
@@ -97,13 +97,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_or(struct atomics *skel)
+static void test_or(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__or__attach(skel);
+	link_fd = atomics_lskel__or__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(or)"))
 		return;
 
@@ -126,13 +126,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_xor(struct atomics *skel)
+static void test_xor(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__xor__attach(skel);
+	link_fd = atomics_lskel__xor__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(xor)"))
 		return;
 
@@ -154,13 +154,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_cmpxchg(struct atomics *skel)
+static void test_cmpxchg(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__cmpxchg__attach(skel);
+	link_fd = atomics_lskel__cmpxchg__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)"))
 		return;
 
@@ -183,13 +183,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_xchg(struct atomics *skel)
+static void test_xchg(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__xchg__attach(skel);
+	link_fd = atomics_lskel__xchg__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(xchg)"))
 		return;
 
@@ -212,10 +212,10 @@ cleanup:
 
 void test_atomics(void)
 {
-	struct atomics *skel;
+	struct atomics_lskel *skel;
 	__u32 duration = 0;
 
-	skel = atomics__open_and_load();
+	skel = atomics_lskel__open_and_load();
 	if (CHECK(!skel, "skel_load", "atomics skeleton failed\n"))
 		return;
 
@@ -225,6 +225,7 @@ void test_atomics(void)
 		test__skip();
 		goto cleanup;
 	}
+	skel->bss->pid = getpid();
 
 	if (test__start_subtest("add"))
 		test_add(skel);
@@ -242,5 +243,5 @@ void test_atomics(void)
 		test_xchg(skel);
 
 cleanup:
-	atomics__destroy(skel);
+	atomics_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 6c511dcd1465..d0bd51eb23c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -5,6 +5,11 @@
 /* this is how USDT semaphore is actually defined, except volatile modifier */
 volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
 
+/* attach point */
+static void method(void) {
+	return ;
+}
+
 void test_attach_probe(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
@@ -33,7 +38,7 @@ void test_attach_probe(void)
 	if (CHECK(base_addr < 0, "get_base_addr",
 		  "failed to find base addr: %zd", base_addr))
 		return;
-	uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr);
+	uprobe_offset = get_uprobe_offset(&method, base_addr);
 
 	ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr);
 	if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
@@ -98,7 +103,7 @@ void test_attach_probe(void)
 		goto cleanup;
 
 	/* trigger & validate uprobe & uretprobe */
-	get_base_addr();
+	method();
 
 	if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res",
 		  "wrong uprobe res: %d\n", skel->bss->uprobe_res))
diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
new file mode 100644
index 000000000000..be73e3de6668
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -0,0 +1,211 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include "bloom_filter_map.skel.h"
+
+static void test_fail_cases(void)
+{
+	__u32 value;
+	int fd, err;
+
+	/* Invalid key size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 4, sizeof(value), 100, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size"))
+		close(fd);
+
+	/* Invalid value size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, 0, 100, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0"))
+		close(fd);
+
+	/* Invalid max entries size */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 0, 0);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size"))
+		close(fd);
+
+	/* Bloom filter maps do not support BPF_F_NO_PREALLOC */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_NO_PREALLOC);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags"))
+		close(fd);
+
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, 0);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter"))
+		return;
+
+	/* Test invalid flags */
+	err = bpf_map_update_elem(fd, NULL, &value, -1);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_EXIST);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_F_LOCK);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_NOEXIST);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, 10000);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	close(fd);
+}
+
+static void test_success_cases(void)
+{
+	char value[11];
+	int fd, err;
+
+	/* Create a map */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_ZERO_SEED | BPF_F_NUMA_NODE);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter success case"))
+		return;
+
+	/* Add a value to the bloom filter */
+	err = bpf_map_update_elem(fd, NULL, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem bloom filter success case"))
+		goto done;
+
+	 /* Lookup a value in the bloom filter */
+	err = bpf_map_lookup_elem(fd, NULL, &value);
+	ASSERT_OK(err, "bpf_map_update_elem bloom filter success case");
+
+done:
+	close(fd);
+}
+
+static void check_bloom(struct bloom_filter_map *skel)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(skel->progs.check_bloom);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+}
+
+static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals,
+			   __u32 nr_rand_vals)
+{
+	int outer_map_fd, inner_map_fd, err, i, key = 0;
+	struct bpf_link *link;
+
+	/* Create a bloom filter map that will be used as the inner map */
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(*rand_vals),
+				      nr_rand_vals, 0);
+	if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map"))
+		return;
+
+	for (i = 0; i < nr_rand_vals; i++) {
+		err = bpf_map_update_elem(inner_map_fd, NULL, rand_vals + i, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to inner_map_fd"))
+			goto done;
+	}
+
+	/* Add the bloom filter map to the outer map */
+	outer_map_fd = bpf_map__fd(skel->maps.outer_map);
+	err = bpf_map_update_elem(outer_map_fd, &key, &inner_map_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "Add bloom filter map to outer map"))
+		goto done;
+
+	/* Attach the bloom_filter_inner_map prog */
+	link = bpf_program__attach(skel->progs.inner_map);
+	if (!ASSERT_OK_PTR(link, "link"))
+		goto delete_inner_map;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+
+delete_inner_map:
+	/* Ensure the inner bloom filter map can be deleted */
+	err = bpf_map_delete_elem(outer_map_fd, &key);
+	ASSERT_OK(err, "Delete inner bloom filter map");
+
+done:
+	close(inner_map_fd);
+}
+
+static int setup_progs(struct bloom_filter_map **out_skel, __u32 **out_rand_vals,
+		       __u32 *out_nr_rand_vals)
+{
+	struct bloom_filter_map *skel;
+	int random_data_fd, bloom_fd;
+	__u32 *rand_vals = NULL;
+	__u32 map_size, val;
+	int err, i;
+
+	/* Set up a bloom filter map skeleton */
+	skel = bloom_filter_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bloom_filter_map__open_and_load"))
+		return -EINVAL;
+
+	/* Set up rand_vals */
+	map_size = bpf_map__max_entries(skel->maps.map_random_data);
+	rand_vals = malloc(sizeof(*rand_vals) * map_size);
+	if (!rand_vals) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	/* Generate random values and populate both skeletons */
+	random_data_fd = bpf_map__fd(skel->maps.map_random_data);
+	bloom_fd = bpf_map__fd(skel->maps.map_bloom);
+	for (i = 0; i < map_size; i++) {
+		val = rand();
+
+		err = bpf_map_update_elem(random_data_fd, &i, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_random_data"))
+			goto error;
+
+		err = bpf_map_update_elem(bloom_fd, NULL, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_bloom"))
+			goto error;
+
+		rand_vals[i] = val;
+	}
+
+	*out_skel = skel;
+	*out_rand_vals = rand_vals;
+	*out_nr_rand_vals = map_size;
+
+	return 0;
+
+error:
+	bloom_filter_map__destroy(skel);
+	if (rand_vals)
+		free(rand_vals);
+	return err;
+}
+
+void test_bloom_filter_map(void)
+{
+	__u32 *rand_vals, nr_rand_vals;
+	struct bloom_filter_map *skel;
+	int err;
+
+	test_fail_cases();
+	test_success_cases();
+
+	err = setup_progs(&skel, &rand_vals, &nr_rand_vals);
+	if (err)
+		return;
+
+	test_inner_map(skel, rand_vals, nr_rand_vals);
+	free(rand_vals);
+
+	check_bloom(skel);
+
+	bloom_filter_map__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
index 85babb0487b3..b52ff8ce34db 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
@@ -179,7 +179,7 @@ done:
 	free_fds(est_fds, nr_est);
 }
 
-void test_bpf_iter_setsockopt(void)
+void serial_test_bpf_iter_setsockopt(void)
 {
 	struct bpf_iter_setsockopt *iter_skel = NULL;
 	struct bpf_cubic *cubic_skel = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 284d5921c345..eb8eeebe6935 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -3,7 +3,7 @@
 
 #define nr_iters 2
 
-void test_bpf_obj_id(void)
+void serial_test_bpf_obj_id(void)
 {
 	const __u64 array_magic_value = 0xfaceb00c;
 	const __u32 array_key = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 3d002c245d2b..27f5d8ea7964 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -39,82 +39,171 @@ struct scale_test_def {
 	bool fails;
 };
 
-void test_bpf_verif_scale(void)
-{
-	struct scale_test_def tests[] = {
-		{ "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ },
-
-		{ "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
-
-		{ "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* full unroll by llvm */
-		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* partial unroll. llvm will unroll loop ~150 times.
-		 * C loop count -> 600.
-		 * Asm loop count -> 4.
-		 * 16k insns in loop body.
-		 * Total of 5 such loops. Total program size ~82k insns.
-		 */
-		{ "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* no unroll at all.
-		 * C loop count -> 600.
-		 * ASM loop count -> 600.
-		 * ~110 insns in loop body.
-		 * Total of 5 such loops. Total program size ~1500 insns.
-		 */
-		{ "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		{ "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "loop4.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "loop5.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "loop6.o", BPF_PROG_TYPE_KPROBE },
-
-		/* partial unroll. 19k insn in a loop.
-		 * Total program size 20.8k insn.
-		 * ~350k processed_insns
-		 */
-		{ "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* no unroll, tiny loops */
-		{ "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* non-inlined subprogs */
-		{ "strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		{ "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
-		{ "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
-
-		{ "test_xdp_loop.o", BPF_PROG_TYPE_XDP },
-		{ "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL },
-	};
+static void scale_test(const char *file,
+		       enum bpf_prog_type attach_type,
+		       bool should_fail)
+{
 	libbpf_print_fn_t old_print_fn = NULL;
-	int err, i;
+	int err;
 
 	if (env.verifier_stats) {
 		test__force_log();
 		old_print_fn = libbpf_set_print(libbpf_debug_print);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		const struct scale_test_def *test = &tests[i];
-
-		if (!test__start_subtest(test->file))
-			continue;
-
-		err = check_load(test->file, test->attach_type);
-		CHECK_FAIL(err && !test->fails);
-	}
+	err = check_load(file, attach_type);
+	if (should_fail)
+		ASSERT_ERR(err, "expect_error");
+	else
+		ASSERT_OK(err, "expect_success");
 
 	if (env.verifier_stats)
 		libbpf_set_print(old_print_fn);
 }
+
+void test_verif_scale1()
+{
+	scale_test("test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale2()
+{
+	scale_test("test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale3()
+{
+	scale_test("test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_pyperf_global()
+{
+	scale_test("pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf_subprogs()
+{
+	scale_test("pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf50()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf100()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf180()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf600()
+{
+	/* partial unroll. llvm will unroll loop ~150 times.
+	 * C loop count -> 600.
+	 * Asm loop count -> 4.
+	 * 16k insns in loop body.
+	 * Total of 5 such loops. Total program size ~82k insns.
+	 */
+	scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf600_nounroll()
+{
+	/* no unroll at all.
+	 * C loop count -> 600.
+	 * ASM loop count -> 600.
+	 * ~110 insns in loop body.
+	 * Total of 5 such loops. Total program size ~1500 insns.
+	 */
+	scale_test("pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop1()
+{
+	scale_test("loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop2()
+{
+	scale_test("loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop3_fail()
+{
+	scale_test("loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */);
+}
+
+void test_verif_scale_loop4()
+{
+	scale_test("loop4.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_loop5()
+{
+	scale_test("loop5.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_loop6()
+{
+	scale_test("loop6.o", BPF_PROG_TYPE_KPROBE, false);
+}
+
+void test_verif_scale_strobemeta()
+{
+	/* partial unroll. 19k insn in a loop.
+	 * Total program size 20.8k insn.
+	 * ~350k processed_insns
+	 */
+	scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_nounroll1()
+{
+	/* no unroll, tiny loops */
+	scale_test("strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_nounroll2()
+{
+	/* no unroll, tiny loops */
+	scale_test("strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_subprogs()
+{
+	/* non-inlined subprogs */
+	scale_test("strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_sysctl_loop1()
+{
+	scale_test("test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+}
+
+void test_verif_scale_sysctl_loop2()
+{
+	scale_test("test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+}
+
+void test_verif_scale_xdp_loop()
+{
+	scale_test("test_xdp_loop.o", BPF_PROG_TYPE_XDP, false);
+}
+
+void test_verif_scale_seg6_loop()
+{
+	scale_test("test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false);
+}
+
+void test_verif_twfw()
+{
+	scale_test("twfw.o", BPF_PROG_TYPE_CGROUP_SKB, false);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 9c85d7d27409..ac596cb06e40 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3662,15 +3662,15 @@ static struct btf_raw_test raw_tests[] = {
 },
 
 {
-	.descr = "tag test #1, struct/member, well-formed",
+	.descr = "decl_tag test #1, struct/member, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -3683,15 +3683,15 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #2, union/member, well-formed",
+	.descr = "decl_tag test #2, union/member, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_UNION_ENC(NAME_TBD, 2, 4),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -3704,13 +3704,13 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #3, variable, well-formed",
+	.descr = "decl_tag test #3, variable, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
 		BTF_VAR_ENC(NAME_TBD, 1, 1),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0global\0tag1\0tag2"),
@@ -3723,16 +3723,16 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #4, func/parameter, well-formed",
+	.descr = "decl_tag test #4, func/parameter, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, -1),
-		BTF_TAG_ENC(NAME_TBD, 3, 0),
-		BTF_TAG_ENC(NAME_TBD, 3, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"),
@@ -3745,11 +3745,11 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #5, invalid value",
+	.descr = "decl_tag test #5, invalid value",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TAG_ENC(0, 2, -1),
+		BTF_DECL_TAG_ENC(0, 2, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag"),
@@ -3764,10 +3764,10 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid value",
 },
 {
-	.descr = "tag test #6, invalid target type",
+	.descr = "decl_tag test #6, invalid target type",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
-		BTF_TAG_ENC(NAME_TBD, 1, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 1, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0tag1"),
@@ -3782,11 +3782,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid type",
 },
 {
-	.descr = "tag test #7, invalid vlen",
+	.descr = "decl_tag test #7, invalid vlen",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3801,11 +3801,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "vlen != 0",
 },
 {
-	.descr = "tag test #8, invalid kflag",
+	.descr = "decl_tag test #8, invalid kflag",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3820,11 +3820,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid btf_info kind_flag",
 },
 {
-	.descr = "tag test #9, var, invalid component_idx",
+	.descr = "decl_tag test #9, var, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag"),
@@ -3839,13 +3839,13 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #10, struct member, invalid component_idx",
+	.descr = "decl_tag test #10, struct member, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
-		BTF_TAG_ENC(NAME_TBD, 2, 2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0m1\0m2\0tag"),
@@ -3860,14 +3860,14 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #11, func parameter, invalid component_idx",
+	.descr = "decl_tag test #11, func parameter, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, 2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
@@ -3882,14 +3882,14 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #12, < -1 component_idx",
+	.descr = "decl_tag test #12, < -1 component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, -2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
@@ -3903,6 +3903,42 @@ static struct btf_raw_test raw_tests[] = {
 	.btf_load_err = true,
 	.err_str = "Invalid component_idx",
 },
+{
+	.descr = "decl_tag test #13, typedef, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0t\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
+{
+	.descr = "decl_tag test #14, typedef, invalid component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
 
 }; /* struct btf_raw_test raw_tests[] */
 
@@ -4511,7 +4547,7 @@ static void do_test_file(unsigned int test_num)
 	if (CHECK(err, "obj: %d", err))
 		return;
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	if (CHECK(!prog, "Cannot find bpf_prog")) {
 		err = -1;
 		goto done;
@@ -6672,9 +6708,9 @@ const struct btf_dedup_test dedup_tests[] = {
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
 			/* tag -> [3] struct s */
-			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
 			/* tag -> [3] struct s, member 1 */
-			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1),				/* [8] */
 
 			/* full copy of the above */
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [9] */
@@ -6689,8 +6725,8 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_PTR_ENC(14),						/* [13] */
 			BTF_CONST_ENC(9),						/* [14] */
 			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [15] */
-			BTF_TAG_ENC(NAME_NTH(2), 11, -1),				/* [16] */
-			BTF_TAG_ENC(NAME_NTH(2), 11, 1),				/* [17] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1),				/* [16] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1),				/* [17] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"),
@@ -6714,8 +6750,8 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_PTR_ENC(6),							/* [5] */
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
-			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
-			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1),				/* [8] */
 			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [9] */
 			BTF_END_RAW,
 		},
@@ -6841,11 +6877,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
-			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 7, -1),				/* [17] decl_tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q"),
 	},
 	.expect = {
 		.raw_types = {
@@ -6869,11 +6906,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
-			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 7, -1),				/* [17] decl_tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
@@ -7036,14 +7074,14 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
 			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
 			/* tag -> t */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
 			/* tag -> func */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [7] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [8] */
 			/* tag -> func arg a1 */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [9] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [10] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
@@ -7056,9 +7094,9 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
 			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [7] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
@@ -7084,17 +7122,17 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 			BTF_FUNC_ENC(NAME_NTH(3), 4),			/* [5] */
 			/* tag -> f: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1),		/* [7] */
 			/* tag -> f/a2: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [8] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1),		/* [9] */
 			/* tag -> f: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 5, -1),		/* [10] */
-			BTF_TAG_ENC(NAME_NTH(6), 5, -1),		/* [11] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1),		/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1),		/* [11] */
 			/* tag -> f/a2: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 5, 1),			/* [12] */
-			BTF_TAG_ENC(NAME_NTH(6), 5, 1),			/* [13] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1),		/* [12] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1),		/* [13] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
@@ -7106,12 +7144,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 			BTF_FUNC_ENC(NAME_NTH(3), 2),			/* [3] */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [7] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [8] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1),		/* [9] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
@@ -7133,17 +7171,17 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
 			/* tag -> t: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			/* tag -> t/m2: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1),		/* [7] */
 			/* tag -> t: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [8] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1),		/* [9] */
 			/* tag -> t/m2: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [10] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [11] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1),		/* [11] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -7154,12 +7192,12 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),		/* [2] */
 				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
-			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [3] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(6), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
-			BTF_TAG_ENC(NAME_NTH(6), 2, 1),			/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [3] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1),		/* [8] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -7168,6 +7206,39 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dont_resolve_fwds = false,
 	},
 },
+{
+	.descr = "dedup: typedef tags",
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [3] */
+			/* tag -> t: tag1, tag2 */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1),		/* [5] */
+			/* tag -> t: tag1, tag3 */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [7] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1),		/* [3] */
+			BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
 
 };
 
@@ -7202,8 +7273,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
-	case BTF_KIND_TAG:
-		return base_size + sizeof(struct btf_tag);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind);
 		return -EINVAL;
@@ -7274,8 +7345,8 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	test_btf_data = btf__get_raw_data(test_btf, &test_btf_size);
-	expect_btf_data = btf__get_raw_data(expect_btf, &expect_btf_size);
+	test_btf_data = btf__raw_data(test_btf, &test_btf_size);
+	expect_btf_data = btf__raw_data(expect_btf, &expect_btf_size);
 	if (CHECK(test_btf_size != expect_btf_size,
 		  "test_btf_size:%u != expect_btf_size:%u",
 		  test_btf_size, expect_btf_size)) {
@@ -7329,8 +7400,8 @@ static void do_test_dedup(unsigned int test_num)
 		expect_str_cur += expect_len + 1;
 	}
 
-	test_nr_types = btf__get_nr_types(test_btf);
-	expect_nr_types = btf__get_nr_types(expect_btf);
+	test_nr_types = btf__type_cnt(test_btf);
+	expect_nr_types = btf__type_cnt(expect_btf);
 	if (CHECK(test_nr_types != expect_nr_types,
 		  "test_nr_types:%u != expect_nr_types:%u",
 		  test_nr_types, expect_nr_types)) {
@@ -7338,7 +7409,7 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	for (i = 1; i <= test_nr_types; i++) {
+	for (i = 1; i < test_nr_types; i++) {
 		const struct btf_type *test_type, *expect_type;
 		int test_size, expect_size;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 87f9df653e4e..aa76360d8f49 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -27,7 +27,7 @@ static struct btf_dump_test_case {
 static int btf_dump_all_types(const struct btf *btf,
 			      const struct btf_dump_opts *opts)
 {
-	size_t type_cnt = btf__get_nr_types(btf);
+	size_t type_cnt = btf__type_cnt(btf);
 	struct btf_dump *d;
 	int err = 0, id;
 
@@ -36,7 +36,7 @@ static int btf_dump_all_types(const struct btf *btf,
 	if (err)
 		return err;
 
-	for (id = 1; id <= type_cnt; id++) {
+	for (id = 1; id < type_cnt; id++) {
 		err = btf_dump__dump_type(d, id);
 		if (err)
 			goto done;
@@ -133,7 +133,7 @@ static char *dump_buf;
 static size_t dump_buf_sz;
 static FILE *dump_buf_file;
 
-void test_btf_dump_incremental(void)
+static void test_btf_dump_incremental(void)
 {
 	struct btf *btf = NULL;
 	struct btf_dump *d = NULL;
@@ -171,7 +171,7 @@ void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "x", 2, 0, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
@@ -210,7 +210,7 @@ void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "s", 3, 32, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
@@ -778,8 +778,10 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
 				   char *str)
 {
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
 			  "int cpu_number = (int)100", 100);
+#endif
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT,
 			  "static int cpu_profile_flip = (int)2", 2);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
index 8ab5d3e358dd..8afbf3d0b89a 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_endian.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
@@ -7,12 +7,12 @@
 #include <bpf/btf.h>
 
 void test_btf_endian() {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	enum btf_endianness endian = BTF_LITTLE_ENDIAN;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	enum btf_endianness endian = BTF_BIG_ENDIAN;
 #else
-#error "Unrecognized __BYTE_ORDER"
+#error "Unrecognized __BYTE_ORDER__"
 #endif
 	enum btf_endianness swap_endian = 1 - endian;
 	struct btf *btf = NULL, *swap_btf = NULL;
@@ -32,7 +32,7 @@ void test_btf_endian() {
 	ASSERT_EQ(btf__endianness(btf), swap_endian, "endian");
 
 	/* Get raw BTF data in non-native endianness... */
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
 		goto err_out;
 
@@ -42,9 +42,9 @@ void test_btf_endian() {
 		goto err_out;
 
 	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
-	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+	ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types");
 
-	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz);
 	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
 		goto err_out;
 
@@ -58,7 +58,7 @@ void test_btf_endian() {
 
 	/* swap it back to native endianness */
 	btf__set_endianness(swap_btf, endian);
-	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz);
 	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
 		goto err_out;
 
@@ -75,7 +75,7 @@ void test_btf_endian() {
 	swap_btf = NULL;
 
 	btf__set_endianness(btf, swap_endian);
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
 		goto err_out;
 
@@ -85,7 +85,7 @@ void test_btf_endian() {
 		goto err_out;
 
 	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
-	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+	ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types");
 
 	/* the type should appear as if it was stored in native endianness */
 	t = btf__type_by_id(swap_btf, var_id);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
index ca7c2a91610a..b1ffe61f2aa9 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -72,7 +72,7 @@ void test_btf_split() {
 	d = btf_dump__new(btf2, NULL, &opts, btf_dump_printf);
 	if (!ASSERT_OK_PTR(d, "btf_dump__new"))
 		goto cleanup;
-	for (i = 1; i <= btf__get_nr_types(btf2); i++) {
+	for (i = 1; i < btf__type_cnt(btf2); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 76548eecce2c..b912eeb0b6b4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -4,19 +4,15 @@
 #include <bpf/btf.h>
 #include "btf_helpers.h"
 
-void test_btf_write() {
+static void gen_btf(struct btf *btf)
+{
 	const struct btf_var_secinfo *vi;
 	const struct btf_type *t;
 	const struct btf_member *m;
 	const struct btf_enum *v;
 	const struct btf_param *p;
-	struct btf *btf;
 	int id, err, str_off;
 
-	btf = btf__new_empty();
-	if (!ASSERT_OK_PTR(btf, "new_empty"))
-		return;
-
 	str_off = btf__find_str(btf, "int");
 	ASSERT_EQ(str_off, -ENOENT, "int_str_missing_off");
 
@@ -281,26 +277,159 @@ void test_btf_write() {
 		     "[17] DATASEC 'datasec1' size=12 vlen=1\n"
 		     "\ttype_id=1 offset=4 size=8", "raw_dump");
 
-	/* TAG */
-	id = btf__add_tag(btf, "tag1", 16, -1);
+	/* DECL_TAG */
+	id = btf__add_decl_tag(btf, "tag1", 16, -1);
 	ASSERT_EQ(id, 18, "tag_id");
 	t = btf__type_by_id(btf, 18);
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value");
-	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind");
 	ASSERT_EQ(t->type, 16, "tag_type");
-	ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx");
+	ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx");
 	ASSERT_STREQ(btf_type_raw_dump(btf, 18),
-		     "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump");
+		     "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump");
 
-	id = btf__add_tag(btf, "tag2", 14, 1);
+	id = btf__add_decl_tag(btf, "tag2", 14, 1);
 	ASSERT_EQ(id, 19, "tag_id");
 	t = btf__type_by_id(btf, 19);
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value");
-	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind");
 	ASSERT_EQ(t->type, 14, "tag_type");
-	ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx");
+	ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx");
 	ASSERT_STREQ(btf_type_raw_dump(btf, 19),
-		     "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
+		     "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
+}
+
+static void test_btf_add()
+{
+	struct btf *btf;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "new_empty"))
+		return;
+
+	gen_btf(btf);
+
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] CONST '(anon)' type_id=5",
+		"[4] VOLATILE '(anon)' type_id=3",
+		"[5] RESTRICT '(anon)' type_id=4",
+		"[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10",
+		"[7] STRUCT 's1' size=8 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=32 bitfield_size=16",
+		"[8] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
+		"[9] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[10] FWD 'struct_fwd' fwd_kind=struct",
+		"[11] FWD 'union_fwd' fwd_kind=union",
+		"[12] ENUM 'enum_fwd' size=4 vlen=0",
+		"[13] TYPEDEF 'typedef1' type_id=1",
+		"[14] FUNC 'func1' type_id=15 linkage=global",
+		"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=2",
+		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
+		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=1 offset=4 size=8",
+		"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] DECL_TAG 'tag2' type_id=14 component_idx=1");
 
 	btf__free(btf);
 }
+
+static void test_btf_add_btf()
+{
+	struct btf *btf1 = NULL, *btf2 = NULL;
+	int id;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "btf1"))
+		return;
+
+	btf2 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf2, "btf2"))
+		goto cleanup;
+
+	gen_btf(btf1);
+	gen_btf(btf2);
+
+	id = btf__add_btf(btf1, btf2);
+	if (!ASSERT_EQ(id, 20, "id"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] CONST '(anon)' type_id=5",
+		"[4] VOLATILE '(anon)' type_id=3",
+		"[5] RESTRICT '(anon)' type_id=4",
+		"[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10",
+		"[7] STRUCT 's1' size=8 vlen=2\n"
+		"\t'f1' type_id=1 bits_offset=0\n"
+		"\t'f2' type_id=1 bits_offset=32 bitfield_size=16",
+		"[8] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
+		"[9] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[10] FWD 'struct_fwd' fwd_kind=struct",
+		"[11] FWD 'union_fwd' fwd_kind=union",
+		"[12] ENUM 'enum_fwd' size=4 vlen=0",
+		"[13] TYPEDEF 'typedef1' type_id=1",
+		"[14] FUNC 'func1' type_id=15 linkage=global",
+		"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=2",
+		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
+		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=1 offset=4 size=8",
+		"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] DECL_TAG 'tag2' type_id=14 component_idx=1",
+
+		/* types appended from the second BTF */
+		"[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[21] PTR '(anon)' type_id=20",
+		"[22] CONST '(anon)' type_id=24",
+		"[23] VOLATILE '(anon)' type_id=22",
+		"[24] RESTRICT '(anon)' type_id=23",
+		"[25] ARRAY '(anon)' type_id=21 index_type_id=20 nr_elems=10",
+		"[26] STRUCT 's1' size=8 vlen=2\n"
+		"\t'f1' type_id=20 bits_offset=0\n"
+		"\t'f2' type_id=20 bits_offset=32 bitfield_size=16",
+		"[27] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=20 bits_offset=0 bitfield_size=16",
+		"[28] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[29] FWD 'struct_fwd' fwd_kind=struct",
+		"[30] FWD 'union_fwd' fwd_kind=union",
+		"[31] ENUM 'enum_fwd' size=4 vlen=0",
+		"[32] TYPEDEF 'typedef1' type_id=20",
+		"[33] FUNC 'func1' type_id=34 linkage=global",
+		"[34] FUNC_PROTO '(anon)' ret_type_id=20 vlen=2\n"
+		"\t'p1' type_id=20\n"
+		"\t'p2' type_id=21",
+		"[35] VAR 'var1' type_id=20, linkage=global-alloc",
+		"[36] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=20 offset=4 size=8",
+		"[37] DECL_TAG 'tag1' type_id=35 component_idx=-1",
+		"[38] DECL_TAG 'tag2' type_id=33 component_idx=1");
+
+cleanup:
+	btf__free(btf1);
+	btf__free(btf2);
+}
+
+void test_btf_write()
+{
+	if (test__start_subtest("btf_add"))
+		test_btf_add();
+	if (test__start_subtest("btf_add_btf"))
+		test_btf_add_btf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
index 876be0ecb654..621c57222191 100644
--- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -363,7 +363,7 @@ close_bpf_object:
 	cg_storage_multi_shared__destroy(obj);
 }
 
-void test_cg_storage_multi(void)
+void serial_test_cg_storage_multi(void)
 {
 	int parent_cgroup_fd = -1, child_cgroup_fd = -1;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
index 70e94e783070..5de485c7370f 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -21,7 +21,7 @@ static int prog_load(void)
 			       bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
-void test_cgroup_attach_autodetach(void)
+void serial_test_cgroup_attach_autodetach(void)
 {
 	__u32 duration = 0, prog_cnt = 4, attach_flags;
 	int allow_prog[2] = {-1};
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index 20bb8831dda6..731bea84d8ed 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -74,7 +74,7 @@ static int prog_load_cnt(int verdict, int val)
 	return ret;
 }
 
-void test_cgroup_attach_multi(void)
+void serial_test_cgroup_attach_multi(void)
 {
 	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
 	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
index 9e96f8d87fea..10d3c33821a7 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
@@ -23,7 +23,7 @@ static int prog_load(int verdict)
 			       bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
-void test_cgroup_attach_override(void)
+void serial_test_cgroup_attach_override(void)
 {
 	int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1;
 	__u32 duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 9091524131d6..9e6e6aad347c 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -24,7 +24,7 @@ int ping_and_check(int exp_calls, int exp_alt_calls)
 	return 0;
 }
 
-void test_cgroup_link(void)
+void serial_test_cgroup_link(void)
 {
 	struct {
 		const char *path;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index ab3b9bc5e6d1..9026b42914d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -46,7 +46,7 @@ void test_cgroup_v1v2(void)
 {
 	struct network_helper_opts opts = {};
 	int server_fd, client_fd, cgroup_fd;
-	static const int port = 60123;
+	static const int port = 60120;
 
 	/* Step 1: Check base connectivity works without any BPF. */
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 012068f33a0a..f73e6e36b74d 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -195,7 +195,7 @@ cleanup:
 	test_check_mtu__destroy(skel);
 }
 
-void test_check_mtu(void)
+void serial_test_check_mtu(void)
 {
 	__u32 mtu_lo;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_autosize.c b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
index 3d4b2a358d47..1dfe14ff6aa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_autosize.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
@@ -112,7 +112,7 @@ void test_core_autosize(void)
 	if (!ASSERT_OK_PTR(f, "btf_fdopen"))
 		goto cleanup;
 
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data"))
 		goto cleanup;
 	written = fwrite(raw_data, 1, raw_sz, f);
@@ -163,7 +163,7 @@ void test_core_autosize(void)
 
 	usleep(1);
 
-	bss_map = bpf_object__find_map_by_name(skel->obj, "test_cor.bss");
+	bss_map = bpf_object__find_map_by_name(skel->obj, ".bss");
 	if (!ASSERT_OK_PTR(bss_map, "bss_map_find"))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 763302e63a29..55ec85ba7375 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -381,7 +381,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test)
 	exp->local_anon_void_ptr = -1;
 	exp->local_anon_arr = -1;
 
-	for (i = 1; i <= btf__get_nr_types(local_btf); i++)
+	for (i = 1; i < btf__type_cnt(local_btf); i++)
 	{
 		t = btf__type_by_id(local_btf, i);
 		/* we are interested only in anonymous types */
@@ -867,7 +867,7 @@ void test_core_reloc(void)
 			goto cleanup;
 		}
 
-		data_map = bpf_object__find_map_by_name(obj, "test_cor.bss");
+		data_map = bpf_object__find_map_by_name(obj, ".bss");
 		if (CHECK(!data_map, "find_data_map", "data map not found\n"))
 			goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
new file mode 100644
index 000000000000..cbaa44ffb8c6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+#include "dummy_st_ops.skel.h"
+
+/* Need to keep consistent with definition in include/linux/bpf.h */
+struct bpf_dummy_ops_state {
+	int val;
+};
+
+static void test_dummy_st_ops_attach(void)
+{
+	struct dummy_st_ops *skel;
+	struct bpf_link *link;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.dummy_1);
+	ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_init_ret_value(void)
+{
+	__u64 args[1] = {0};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_1);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_init_ptr_arg(void)
+{
+	int exp_retval = 0xbeef;
+	struct bpf_dummy_ops_state in_state = {
+		.val = exp_retval,
+	};
+	__u64 args[1] = {(unsigned long)&in_state};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_1);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret");
+	ASSERT_EQ(attr.retval, exp_retval, "test_ret");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_multiple_args(void)
+{
+	__u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+	size_t i;
+	char name[8];
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_2);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	for (i = 0; i < ARRAY_SIZE(args); i++) {
+		snprintf(name, sizeof(name), "arg %zu", i);
+		ASSERT_EQ(skel->bss->test_2_args[i], args[i], name);
+	}
+
+	dummy_st_ops__destroy(skel);
+}
+
+void test_dummy_st_ops(void)
+{
+	if (test__start_subtest("dummy_st_ops_attach"))
+		test_dummy_st_ops_attach();
+	if (test__start_subtest("dummy_init_ret_value"))
+		test_dummy_init_ret_value();
+	if (test__start_subtest("dummy_init_ptr_arg"))
+		test_dummy_init_ptr_arg();
+	if (test__start_subtest("dummy_multiple_args"))
+		test_dummy_multiple_args();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 91154c2ba256..4374ac8a8a91 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -6,23 +6,23 @@
 
 void test_fentry_fexit(void)
 {
-	struct fentry_test *fentry_skel = NULL;
-	struct fexit_test *fexit_skel = NULL;
+	struct fentry_test_lskel *fentry_skel = NULL;
+	struct fexit_test_lskel *fexit_skel = NULL;
 	__u64 *fentry_res, *fexit_res;
 	__u32 duration = 0, retval;
 	int err, prog_fd, i;
 
-	fentry_skel = fentry_test__open_and_load();
+	fentry_skel = fentry_test_lskel__open_and_load();
 	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
 		goto close_prog;
-	fexit_skel = fexit_test__open_and_load();
+	fexit_skel = fexit_test_lskel__open_and_load();
 	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
 		goto close_prog;
 
-	err = fentry_test__attach(fentry_skel);
+	err = fentry_test_lskel__attach(fentry_skel);
 	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
 		goto close_prog;
-	err = fexit_test__attach(fexit_skel);
+	err = fexit_test_lskel__attach(fexit_skel);
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto close_prog;
 
@@ -44,6 +44,6 @@ void test_fentry_fexit(void)
 	}
 
 close_prog:
-	fentry_test__destroy(fentry_skel);
-	fexit_test__destroy(fexit_skel);
+	fentry_test_lskel__destroy(fentry_skel);
+	fexit_test_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 174c89e7456e..12921b3850d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -3,19 +3,19 @@
 #include <test_progs.h>
 #include "fentry_test.lskel.h"
 
-static int fentry_test(struct fentry_test *fentry_skel)
+static int fentry_test(struct fentry_test_lskel *fentry_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
 	int link_fd;
 	__u64 *result;
 
-	err = fentry_test__attach(fentry_skel);
+	err = fentry_test_lskel__attach(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_attach"))
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link_fd = fentry_test__test1__attach(fentry_skel);
+	link_fd = fentry_test_lskel__test1__attach(fentry_skel);
 	if (!ASSERT_LT(link_fd, 0, "fentry_attach_link"))
 		return -1;
 
@@ -31,7 +31,7 @@ static int fentry_test(struct fentry_test *fentry_skel)
 			return -1;
 	}
 
-	fentry_test__detach(fentry_skel);
+	fentry_test_lskel__detach(fentry_skel);
 
 	/* zero results for re-attach test */
 	memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss));
@@ -40,10 +40,10 @@ static int fentry_test(struct fentry_test *fentry_skel)
 
 void test_fentry_test(void)
 {
-	struct fentry_test *fentry_skel = NULL;
+	struct fentry_test_lskel *fentry_skel = NULL;
 	int err;
 
-	fentry_skel = fentry_test__open_and_load();
+	fentry_skel = fentry_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
 		goto cleanup;
 
@@ -55,5 +55,5 @@ void test_fentry_test(void)
 	ASSERT_OK(err, "fentry_second_attach");
 
 cleanup:
-	fentry_test__destroy(fentry_skel);
+	fentry_test_lskel__destroy(fentry_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index c7c1816899bf..9cff14a23bb7 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -285,7 +285,7 @@ static void test_fmod_ret_freplace(void)
 	if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open"))
 		goto out;
 
-	prog = bpf_program__next(NULL, freplace_obj);
+	prog = bpf_object__next_program(freplace_obj, NULL);
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "freplace__set_attach_target");
 
@@ -302,7 +302,7 @@ static void test_fmod_ret_freplace(void)
 		goto out;
 
 	attach_prog_fd = bpf_program__fd(prog);
-	prog = bpf_program__next(NULL, fmod_obj);
+	prog = bpf_object__next_program(fmod_obj, NULL);
 	err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL);
 	ASSERT_OK(err, "fmod_ret_set_attach_target");
 
@@ -352,7 +352,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "set_attach_target");
 
@@ -380,7 +380,8 @@ static void test_func_map_prog_compatibility(void)
 				     "./test_attach_probe.o");
 }
 
-void test_fexit_bpf2bpf(void)
+/* NOTE: affect other tests, must run in serial mode */
+void serial_test_fexit_bpf2bpf(void)
 {
 	if (test__start_subtest("target_no_callees"))
 		test_target_no_callees();
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index 4e7f4b42ea29..f949647dbbc2 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -10,7 +10,7 @@
 
 static int do_sleep(void *skel)
 {
-	struct fexit_sleep *fexit_skel = skel;
+	struct fexit_sleep_lskel *fexit_skel = skel;
 	struct timespec ts1 = { .tv_nsec = 1 };
 	struct timespec ts2 = { .tv_sec = 10 };
 
@@ -25,16 +25,16 @@ static char child_stack[STACK_SIZE];
 
 void test_fexit_sleep(void)
 {
-	struct fexit_sleep *fexit_skel = NULL;
+	struct fexit_sleep_lskel *fexit_skel = NULL;
 	int wstatus, duration = 0;
 	pid_t cpid;
 	int err, fexit_cnt;
 
-	fexit_skel = fexit_sleep__open_and_load();
+	fexit_skel = fexit_sleep_lskel__open_and_load();
 	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
 		goto cleanup;
 
-	err = fexit_sleep__attach(fexit_skel);
+	err = fexit_sleep_lskel__attach(fexit_skel);
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto cleanup;
 
@@ -60,7 +60,7 @@ void test_fexit_sleep(void)
 	 */
 	close(fexit_skel->progs.nanosleep_fentry.prog_fd);
 	close(fexit_skel->progs.nanosleep_fexit.prog_fd);
-	fexit_sleep__detach(fexit_skel);
+	fexit_sleep_lskel__detach(fexit_skel);
 
 	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
 	kill(cpid, 9);
@@ -78,5 +78,5 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 cleanup:
-	fexit_sleep__destroy(fexit_skel);
+	fexit_sleep_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index af3dba726701..d4887d8bb396 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -3,19 +3,19 @@
 #include <test_progs.h>
 #include "fexit_test.lskel.h"
 
-static int fexit_test(struct fexit_test *fexit_skel)
+static int fexit_test(struct fexit_test_lskel *fexit_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
 	int link_fd;
 	__u64 *result;
 
-	err = fexit_test__attach(fexit_skel);
+	err = fexit_test_lskel__attach(fexit_skel);
 	if (!ASSERT_OK(err, "fexit_attach"))
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link_fd = fexit_test__test1__attach(fexit_skel);
+	link_fd = fexit_test_lskel__test1__attach(fexit_skel);
 	if (!ASSERT_LT(link_fd, 0, "fexit_attach_link"))
 		return -1;
 
@@ -31,7 +31,7 @@ static int fexit_test(struct fexit_test *fexit_skel)
 			return -1;
 	}
 
-	fexit_test__detach(fexit_skel);
+	fexit_test_lskel__detach(fexit_skel);
 
 	/* zero results for re-attach test */
 	memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss));
@@ -40,10 +40,10 @@ static int fexit_test(struct fexit_test *fexit_skel)
 
 void test_fexit_test(void)
 {
-	struct fexit_test *fexit_skel = NULL;
+	struct fexit_test_lskel *fexit_skel = NULL;
 	int err;
 
-	fexit_skel = fexit_test__open_and_load();
+	fexit_skel = fexit_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
 		goto cleanup;
 
@@ -55,5 +55,5 @@ void test_fexit_test(void)
 	ASSERT_OK(err, "fexit_second_attach");
 
 cleanup:
-	fexit_test__destroy(fexit_skel);
+	fexit_test_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
index 0e8a4d2f023d..6093728497c7 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-void test_flow_dissector_load_bytes(void)
+void serial_test_flow_dissector_load_bytes(void)
 {
 	struct bpf_flow_keys flow_keys;
 	__u32 duration = 0, retval, size;
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 3931ede5c534..f0c6c226aba8 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -628,7 +628,7 @@ out_close:
 	}
 }
 
-void test_flow_dissector_reattach(void)
+void serial_test_flow_dissector_reattach(void)
 {
 	int err, new_net, saved_net;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index 67e86f8d8677..3948da12a528 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -6,6 +6,30 @@
 static int *pfd_array;
 static int cpu_cnt;
 
+static bool is_hypervisor(void)
+{
+	char *line = NULL;
+	bool ret = false;
+	size_t len;
+	FILE *fp;
+
+	fp = fopen("/proc/cpuinfo", "r");
+	if (!fp)
+		return false;
+
+	while (getline(&line, &len, fp) != -1) {
+		if (!strncmp(line, "flags", 5)) {
+			if (strstr(line, "hypervisor") != NULL)
+				ret = true;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(fp);
+	return ret;
+}
+
 static int create_perf_events(void)
 {
 	struct perf_event_attr attr = {0};
@@ -49,11 +73,17 @@ static void close_perf_events(void)
 	free(pfd_array);
 }
 
-void test_get_branch_snapshot(void)
+void serial_test_get_branch_snapshot(void)
 {
 	struct get_branch_snapshot *skel = NULL;
 	int err;
 
+	/* Skip the test before we fix LBR snapshot for hypervisor. */
+	if (is_hypervisor()) {
+		test__skip();
+		return;
+	}
+
 	if (create_perf_events()) {
 		test__skip();  /* system doesn't support LBR */
 		goto cleanup;
@@ -67,9 +97,10 @@ void test_get_branch_snapshot(void)
 	if (!ASSERT_OK(err, "kallsyms_find"))
 		goto cleanup;
 
-	err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high);
-	if (!ASSERT_OK(err, "kallsyms_find_next"))
-		goto cleanup;
+	/* Just a guess for the end of this function, as module functions
+	 * in /proc/kallsyms could come in any order.
+	 */
+	skel->bss->address_high = skel->bss->address_low + 128;
 
 	err = get_branch_snapshot__attach(skel);
 	if (!ASSERT_OK(err, "get_branch_snapshot__attach"))
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index 9efa7e50eab2..afd8639f9a94 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -103,11 +103,18 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration)
 static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration)
 {
 	int err = -ENOMEM, map_fd, zero = 0;
-	struct bpf_map *map;
+	struct bpf_map *map, *map2;
 	__u8 *buff;
 
 	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
-	if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
+	if (!ASSERT_OK_PTR(map, "map"))
+		return;
+	if (!ASSERT_TRUE(bpf_map__is_internal(map), "is_internal"))
+		return;
+
+	/* ensure we can lookup internal maps by their ELF names */
+	map2 = bpf_object__find_map_by_name(obj, ".rodata");
+	if (!ASSERT_EQ(map, map2, "same_maps"))
 		return;
 
 	map_fd = bpf_map__fd(map);
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index ee46b11f1f9a..1db86eab101b 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -16,7 +16,7 @@ void test_global_data_init(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
+	map = bpf_object__find_map_by_name(obj, ".rodata");
 	if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
 		goto out;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index ddfb6bf97152..01e51d16c8b8 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -48,7 +48,8 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 	*(bool *)ctx = true;
 }
 
-void test_kfree_skb(void)
+/* TODO: fix kernel panic caused by this test in parallel mode */
+void serial_test_kfree_skb(void)
 {
 	struct __sk_buff skb = {};
 	struct bpf_prog_test_run_attr tattr = {
@@ -92,7 +93,7 @@ void test_kfree_skb(void)
 	if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n"))
 		goto close_prog;
 
-	global_data = bpf_object__find_map_by_name(obj2, "kfree_sk.bss");
+	global_data = bpf_object__find_map_by_name(obj2, ".bss");
 	if (CHECK(!global_data, "find global data", "not found\n"))
 		goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 9611f2bc50df..5c9c0176991b 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -7,10 +7,10 @@
 
 static void test_main(void)
 {
-	struct kfunc_call_test *skel;
+	struct kfunc_call_test_lskel *skel;
 	int prog_fd, retval, err;
 
-	skel = kfunc_call_test__open_and_load();
+	skel = kfunc_call_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel"))
 		return;
 
@@ -26,7 +26,7 @@ static void test_main(void)
 	ASSERT_OK(err, "bpf_prog_test_run(test2)");
 	ASSERT_EQ(retval, 3, "test2-retval");
 
-	kfunc_call_test__destroy(skel);
+	kfunc_call_test_lskel__destroy(skel);
 }
 
 static void test_subprog(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index cf3acfa5a91d..79f6bd1e50d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -7,6 +7,7 @@
 #include "test_ksyms_btf.skel.h"
 #include "test_ksyms_btf_null_check.skel.h"
 #include "test_ksyms_weak.skel.h"
+#include "test_ksyms_weak.lskel.h"
 
 static int duration;
 
@@ -89,11 +90,11 @@ static void test_weak_syms(void)
 	int err;
 
 	skel = test_ksyms_weak__open_and_load();
-	if (CHECK(!skel, "test_ksyms_weak__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_weak__open_and_load"))
 		return;
 
 	err = test_ksyms_weak__attach(skel);
-	if (CHECK(err, "test_ksyms_weak__attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_ksyms_weak__attach"))
 		goto cleanup;
 
 	/* trigger tracepoint */
@@ -109,6 +110,33 @@ cleanup:
 	test_ksyms_weak__destroy(skel);
 }
 
+static void test_weak_syms_lskel(void)
+{
+	struct test_ksyms_weak_lskel *skel;
+	struct test_ksyms_weak_lskel__data *data;
+	int err;
+
+	skel = test_ksyms_weak_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_weak_lskel__open_and_load"))
+		return;
+
+	err = test_ksyms_weak_lskel__attach(skel);
+	if (!ASSERT_OK(err, "test_ksyms_weak_lskel__attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	data = skel->data;
+	ASSERT_EQ(data->out__existing_typed, 0, "existing typed ksym");
+	ASSERT_NEQ(data->out__existing_typeless, -1, "existing typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typeless, 0, "nonexistent typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typed, 0, "nonexistent typed ksym");
+
+cleanup:
+	test_ksyms_weak_lskel__destroy(skel);
+}
+
 void test_ksyms_btf(void)
 {
 	int percpu_datasec;
@@ -136,4 +164,7 @@ void test_ksyms_btf(void)
 
 	if (test__start_subtest("weak_ksyms"))
 		test_weak_syms();
+
+	if (test__start_subtest("weak_ksyms_lskel"))
+		test_weak_syms_lskel();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
index 2cd5cded543f..d490ad80eccb 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
@@ -2,30 +2,61 @@
 /* Copyright (c) 2021 Facebook */
 
 #include <test_progs.h>
-#include <bpf/libbpf.h>
-#include <bpf/btf.h>
+#include <network_helpers.h>
 #include "test_ksyms_module.lskel.h"
+#include "test_ksyms_module.skel.h"
 
-static int duration;
-
-void test_ksyms_module(void)
+void test_ksyms_module_lskel(void)
 {
-	struct test_ksyms_module* skel;
+	struct test_ksyms_module_lskel *skel;
+	int retval;
 	int err;
 
-	skel = test_ksyms_module__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!env.has_testmod) {
+		test__skip();
 		return;
+	}
 
-	err = test_ksyms_module__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	skel = test_ksyms_module_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load"))
+		return;
+	err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	if (!ASSERT_OK(err, "bpf_prog_test_run"))
 		goto cleanup;
+	ASSERT_EQ(retval, 0, "retval");
+	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
+cleanup:
+	test_ksyms_module_lskel__destroy(skel);
+}
 
-	usleep(1);
+void test_ksyms_module_libbpf(void)
+{
+	struct test_ksyms_module *skel;
+	int retval, err;
 
-	ASSERT_EQ(skel->bss->triggered, true, "triggered");
-	ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val");
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
 
+	skel = test_ksyms_module__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open"))
+		return;
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4,
+				sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL);
+	if (!ASSERT_OK(err, "bpf_prog_test_run"))
+		goto cleanup;
+	ASSERT_EQ(retval, 0, "retval");
+	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
 cleanup:
 	test_ksyms_module__destroy(skel);
 }
+
+void test_ksyms_module(void)
+{
+	if (test__start_subtest("lskel"))
+		test_ksyms_module_lskel();
+	if (test__start_subtest("libbpf"))
+		test_ksyms_module_libbpf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
index 59adb4715394..7589c03fd26b 100644
--- a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
@@ -541,7 +541,7 @@ close_servers:
 	}
 }
 
-void test_migrate_reuseport(void)
+void serial_test_migrate_reuseport(void)
 {
 	struct test_migrate_reuseport *skel;
 	int i;
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
index 97fec70c600b..b772fe30ce9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/modify_return.c
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -53,7 +53,8 @@ cleanup:
 	modify_return__destroy(skel);
 }
 
-void test_modify_return(void)
+/* TODO: conflict with get_func_ip_test */
+void serial_test_modify_return(void)
 {
 	run_test(0 /* input_retval */,
 		 1 /* want_side_effect */,
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 1797a6e4d6d8..6d0e50dcf47c 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -2,10 +2,36 @@
 /* Copyright (c) 2020 Facebook */
 
 #include <test_progs.h>
+#include <stdbool.h>
 #include "test_module_attach.skel.h"
 
 static int duration;
 
+static int trigger_module_test_writable(int *val)
+{
+	int fd, err;
+	char buf[65];
+	ssize_t rd;
+
+	fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmode_file_open"))
+		return err;
+
+	rd = read(fd, buf, sizeof(buf) - 1);
+	err = -errno;
+	if (!ASSERT_GT(rd, 0, "testmod_file_rd_val")) {
+		close(fd);
+		return err;
+	}
+
+	buf[rd] = '\0';
+	*val = strtol(buf, NULL, 0);
+	close(fd);
+
+	return 0;
+}
+
 static int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
@@ -19,6 +45,7 @@ void test_module_attach(void)
 	struct test_module_attach__bss *bss;
 	struct bpf_link *link;
 	int err;
+	int writable_val = 0;
 
 	skel = test_module_attach__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -51,6 +78,14 @@ void test_module_attach(void)
 	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
 	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
 
+	bss->raw_tp_writable_bare_early_ret = true;
+	bss->raw_tp_writable_bare_out_val = 0xf1f2f3f4;
+	ASSERT_OK(trigger_module_test_writable(&writable_val),
+		  "trigger_writable");
+	ASSERT_EQ(bss->raw_tp_writable_bare_in_val, 1024, "writable_test_in");
+	ASSERT_EQ(bss->raw_tp_writable_bare_out_val, writable_val,
+		  "writable_test_out");
+
 	test_module_attach__detach(skel);
 
 	/* attach fentry/fexit and make sure it get's module reference */
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 2535788e135f..24d493482ffc 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -78,7 +78,8 @@ static void test_ns_current_pid_tgid_new_ns(void)
 		return;
 }
 
-void test_ns_current_pid_tgid(void)
+/* TODO: use a different tracepoint */
+void serial_test_ns_current_pid_tgid(void)
 {
 	if (test__start_subtest("ns_current_pid_tgid_root_ns"))
 		test_current_pid_tgid(NULL);
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 6490e9673002..4e32f3586a75 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -43,9 +43,10 @@ int trigger_on_cpu(int cpu)
 	return 0;
 }
 
-void test_perf_buffer(void)
+void serial_test_perf_buffer(void)
 {
-	int err, on_len, nr_on_cpus = 0, nr_cpus, i;
+	int err, on_len, nr_on_cpus = 0, nr_cpus, i, j;
+	int zero = 0, my_pid = getpid();
 	struct perf_buffer_opts pb_opts = {};
 	struct test_perf_buffer *skel;
 	cpu_set_t cpu_seen;
@@ -71,6 +72,10 @@ void test_perf_buffer(void)
 	if (CHECK(!skel, "skel_load", "skeleton open/load failed\n"))
 		goto out_close;
 
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.my_pid_map), &zero, &my_pid, 0);
+	if (!ASSERT_OK(err, "my_pid_update"))
+		goto out_close;
+
 	/* attach probe */
 	err = test_perf_buffer__attach(skel);
 	if (CHECK(err, "attach_kprobe", "err %d\n", err))
@@ -107,19 +112,19 @@ void test_perf_buffer(void)
 		  "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen)))
 		goto out_free_pb;
 
-	if (CHECK(perf_buffer__buffer_cnt(pb) != nr_cpus, "buf_cnt",
-		  "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_cpus))
+	if (CHECK(perf_buffer__buffer_cnt(pb) != nr_on_cpus, "buf_cnt",
+		  "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_on_cpus))
 		goto out_close;
 
-	for (i = 0; i < nr_cpus; i++) {
+	for (i = 0, j = 0; i < nr_cpus; i++) {
 		if (i >= on_len || !online[i])
 			continue;
 
-		fd = perf_buffer__buffer_fd(pb, i);
+		fd = perf_buffer__buffer_fd(pb, j);
 		CHECK(fd < 0 || last_fd == fd, "fd_check", "last fd %d == fd %d\n", last_fd, fd);
 		last_fd = fd;
 
-		err = perf_buffer__consume_buffer(pb, i);
+		err = perf_buffer__consume_buffer(pb, j);
 		if (CHECK(err, "drain_buf", "cpu %d, err %d\n", i, err))
 			goto out_close;
 
@@ -127,12 +132,13 @@ void test_perf_buffer(void)
 		if (trigger_on_cpu(i))
 			goto out_close;
 
-		err = perf_buffer__consume_buffer(pb, i);
-		if (CHECK(err, "consume_buf", "cpu %d, err %d\n", i, err))
+		err = perf_buffer__consume_buffer(pb, j);
+		if (CHECK(err, "consume_buf", "cpu %d, err %d\n", j, err))
 			goto out_close;
 
 		if (CHECK(!CPU_ISSET(i, &cpu_seen), "cpu_seen", "cpu %d not seen\n", i))
 			goto out_close;
+		j++;
 	}
 
 out_free_pb:
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c
index b1abd0c46607..ede07344f264 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c
@@ -23,7 +23,8 @@ static void burn_cpu(void)
 		++j;
 }
 
-void test_perf_link(void)
+/* TODO: often fails in concurrent mode */
+void serial_test_perf_link(void)
 {
 	struct test_perf_link *skel = NULL;
 	struct perf_event_attr attr;
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
index 52fe157e2a90..abf890d066eb 100644
--- a/tools/testing/selftests/bpf/prog_tests/probe_user.c
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
-void test_probe_user(void)
+/* TODO: corrupts other tests uses connect() */
+void serial_test_probe_user(void)
 {
 	const char *prog_name = "handle_sys_connect";
 	const char *obj_file = "./test_probe_user.o";
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
index 5c45424cac5f..ddefa1192e5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
@@ -3,7 +3,8 @@
 #include <test_progs.h>
 #include <linux/nbd.h>
 
-void test_raw_tp_writable_test_run(void)
+/* NOTE: conflict with other tests. */
+void serial_test_raw_tp_writable_test_run(void)
 {
 	__u32 duration = 0;
 	char error[4096];
diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
index 5f9eaa3ab584..fd5d2ddfb062 100644
--- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
+++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
@@ -37,7 +37,7 @@ void test_rdonly_maps(void)
 	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
 		goto cleanup;
 
-	bss_map = bpf_object__find_map_by_name(obj, "test_rdo.bss");
+	bss_map = bpf_object__find_map_by_name(obj, ".bss");
 	if (CHECK(!bss_map, "find_bss_map", "failed\n"))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/recursion.c b/tools/testing/selftests/bpf/prog_tests/recursion.c
index 0e378d63fe18..f3af2627b599 100644
--- a/tools/testing/selftests/bpf/prog_tests/recursion.c
+++ b/tools/testing/selftests/bpf/prog_tests/recursion.c
@@ -20,18 +20,18 @@ void test_recursion(void)
 		goto out;
 
 	ASSERT_EQ(skel->bss->pass1, 0, "pass1 == 0");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key);
 	ASSERT_EQ(skel->bss->pass1, 1, "pass1 == 1");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key);
 	ASSERT_EQ(skel->bss->pass1, 2, "pass1 == 2");
 
 	ASSERT_EQ(skel->bss->pass2, 0, "pass2 == 0");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key);
 	ASSERT_EQ(skel->bss->pass2, 1, "pass2 == 1");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key);
 	ASSERT_EQ(skel->bss->pass2, 2, "pass2 == 2");
 
-	err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_lookup),
+	err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_delete),
 				     &prog_info, &prog_info_len);
 	if (!ASSERT_OK(err, "get_prog_info"))
 		goto out;
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index f62361306f6d..f4a13d9dd5c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -106,9 +106,9 @@ static int resolve_symbols(void)
 		  "Failed to load BTF from btf_data.o\n"))
 		return -1;
 
-	nr = btf__get_nr_types(btf);
+	nr = btf__type_cnt(btf);
 
-	for (type_id = 1; type_id <= nr; type_id++) {
+	for (type_id = 1; type_id < nr; type_id++) {
 		if (__resolve_symbol(btf, type_id))
 			break;
 	}
@@ -117,14 +117,14 @@ static int resolve_symbols(void)
 	return 0;
 }
 
-int test_resolve_btfids(void)
+void test_resolve_btfids(void)
 {
 	__u32 *test_list, *test_lists[] = { test_list_local, test_list_global };
 	unsigned int i, j;
 	int ret = 0;
 
 	if (resolve_symbols())
-		return -1;
+		return;
 
 	/* Check BTF_ID_LIST(test_list_local) and
 	 * BTF_ID_LIST_GLOBAL(test_list_global) IDs
@@ -138,7 +138,7 @@ int test_resolve_btfids(void)
 				    test_symbols[i].name,
 				    test_list[i], test_symbols[i].id);
 			if (ret)
-				return ret;
+				return;
 		}
 	}
 
@@ -161,9 +161,7 @@ int test_resolve_btfids(void)
 
 		if (i > 0) {
 			if (!ASSERT_LE(test_set.ids[i - 1], test_set.ids[i], "sort_check"))
-				return -1;
+				return;
 		}
 	}
-
-	return ret;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 4706cee84360..9a80fe8a6427 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -58,7 +58,7 @@ static int process_sample(void *ctx, void *data, size_t len)
 	}
 }
 
-static struct test_ringbuf *skel;
+static struct test_ringbuf_lskel *skel;
 static struct ring_buffer *ringbuf;
 
 static void trigger_samples()
@@ -90,13 +90,13 @@ void test_ringbuf(void)
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
 
-	skel = test_ringbuf__open();
+	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
 	skel->maps.ringbuf.max_entries = page_size;
 
-	err = test_ringbuf__load(skel);
+	err = test_ringbuf_lskel__load(skel);
 	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
 		goto cleanup;
 
@@ -154,7 +154,7 @@ void test_ringbuf(void)
 	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
 		goto cleanup;
 
-	err = test_ringbuf__attach(skel);
+	err = test_ringbuf_lskel__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
 		goto cleanup;
 
@@ -292,8 +292,8 @@ void test_ringbuf(void)
 	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
 	      1L, skel->bss->discarded);
 
-	test_ringbuf__detach(skel);
+	test_ringbuf_lskel__detach(skel);
 cleanup:
 	ring_buffer__free(ringbuf);
-	test_ringbuf__destroy(skel);
+	test_ringbuf_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 4efd337d6a3c..3cfc910ab3c1 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -114,7 +114,7 @@ static int prepare_bpf_obj(void)
 	err = bpf_object__load(obj);
 	RET_ERR(err, "load bpf_object", "err:%d\n", err);
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	RET_ERR(!prog, "get first bpf_program", "!prog\n");
 	select_by_skb_data_prog = bpf_program__fd(prog);
 	RET_ERR(select_by_skb_data_prog < 0, "get prog fd",
@@ -858,7 +858,7 @@ out:
 	cleanup();
 }
 
-void test_select_reuseport(void)
+void serial_test_select_reuseport(void)
 {
 	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
 	if (saved_tcp_fo < 0)
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
index 189a34a7addb..15dacfcfaa6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
@@ -25,7 +25,8 @@ static void *worker(void *p)
 	return NULL;
 }
 
-void test_send_signal_sched_switch(void)
+/* NOTE: cause events loss */
+void serial_test_send_signal_sched_switch(void)
 {
 	struct test_send_signal_kern *skel;
 	pthread_t threads[THREAD_COUNT];
diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
index dfcbddcbe4d3..fdfdcff6cbef 100644
--- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c
+++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
@@ -42,7 +42,7 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type)
 	signal(SIGALRM, SIG_DFL);
 }
 
-void test_signal_pending(enum bpf_prog_type prog_type)
+void test_signal_pending(void)
 {
 	test_signal_pending_by_type(BPF_PROG_TYPE_SOCKET_FILTER);
 	test_signal_pending_by_type(BPF_PROG_TYPE_FLOW_DISSECTOR);
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index aee41547e7f4..6db07401bc49 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -598,7 +598,7 @@ close:
 
 static void run_lookup_prog(const struct test *t)
 {
-	int server_fds[MAX_SERVERS] = { -1 };
+	int server_fds[] = { [0 ... MAX_SERVERS - 1] = -1 };
 	int client_fd, reuse_conn_fd = -1;
 	struct bpf_link *lookup_link;
 	int i, err;
@@ -1053,7 +1053,7 @@ static void run_sk_assign(struct test_sk_lookup *skel,
 			  struct bpf_program *lookup_prog,
 			  const char *remote_ip, const char *local_ip)
 {
-	int server_fds[MAX_SERVERS] = { -1 };
+	int server_fds[] = { [0 ... MAX_SERVERS - 1] = -1 };
 	struct bpf_sk_lookup ctx;
 	__u64 server_cookie;
 	int i, err;
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
index 2b392590e8ca..547ae53cde74 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
@@ -105,7 +105,7 @@ out:
 		close(listen_fd);
 }
 
-void test_sk_storage_tracing(void)
+void serial_test_sk_storage_tracing(void)
 {
 	struct test_sk_storage_trace_itself *skel_itself;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
new file mode 100644
index 000000000000..3eefdfed1db9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include <test_progs.h>
+#include <sys/un.h>
+#include "test_skc_to_unix_sock.skel.h"
+
+static const char *sock_path = "@skc_to_unix_sock";
+
+void test_skc_to_unix_sock(void)
+{
+	struct test_skc_to_unix_sock *skel;
+	struct sockaddr_un sockaddr;
+	int err, sockfd = 0;
+
+	skel = test_skc_to_unix_sock__open();
+	if (!ASSERT_OK_PTR(skel, "could not open BPF object"))
+		return;
+
+	skel->rodata->my_pid = getpid();
+
+	err = test_skc_to_unix_sock__load(skel);
+	if (!ASSERT_OK(err, "could not load BPF object"))
+		goto cleanup;
+
+	err = test_skc_to_unix_sock__attach(skel);
+	if (!ASSERT_OK(err, "could not attach BPF object"))
+		goto cleanup;
+
+	/* trigger unix_listen */
+	sockfd = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (!ASSERT_GT(sockfd, 0, "socket failed"))
+		goto cleanup;
+
+	memset(&sockaddr, 0, sizeof(sockaddr));
+	sockaddr.sun_family = AF_UNIX;
+	strncpy(sockaddr.sun_path, sock_path, strlen(sock_path));
+	sockaddr.sun_path[0] = '\0';
+
+	err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr));
+	if (!ASSERT_OK(err, "bind failed"))
+		goto cleanup;
+
+	err = listen(sockfd, 1);
+	if (!ASSERT_OK(err, "listen failed"))
+		goto cleanup;
+
+	ASSERT_EQ(strcmp(skel->bss->path, sock_path), 0, "bpf_skc_to_unix_sock failed");
+
+cleanup:
+	if (sockfd)
+		close(sockfd);
+	test_skc_to_unix_sock__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index fe1e204a65c6..180afd632f4c 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -16,10 +16,13 @@ void test_skeleton(void)
 	struct test_skeleton* skel;
 	struct test_skeleton__bss *bss;
 	struct test_skeleton__data *data;
+	struct test_skeleton__data_dyn *data_dyn;
 	struct test_skeleton__rodata *rodata;
+	struct test_skeleton__rodata_dyn *rodata_dyn;
 	struct test_skeleton__kconfig *kcfg;
 	const void *elf_bytes;
 	size_t elf_bytes_sz = 0;
+	int i;
 
 	skel = test_skeleton__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -30,7 +33,12 @@ void test_skeleton(void)
 
 	bss = skel->bss;
 	data = skel->data;
+	data_dyn = skel->data_dyn;
 	rodata = skel->rodata;
+	rodata_dyn = skel->rodata_dyn;
+
+	ASSERT_STREQ(bpf_map__name(skel->maps.rodata_dyn), ".rodata.dyn", "rodata_dyn_name");
+	ASSERT_STREQ(bpf_map__name(skel->maps.data_dyn), ".data.dyn", "data_dyn_name");
 
 	/* validate values are pre-initialized correctly */
 	CHECK(data->in1 != -1, "in1", "got %d != exp %d\n", data->in1, -1);
@@ -46,6 +54,12 @@ void test_skeleton(void)
 	CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0);
 	CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0);
 
+	ASSERT_EQ(rodata_dyn->in_dynarr_sz, 0, "in_dynarr_sz");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(rodata_dyn->in_dynarr[i], -(i + 1), "in_dynarr");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(data_dyn->out_dynarr[i], i + 1, "out_dynarr");
+
 	/* validate we can pre-setup global variables, even in .bss */
 	data->in1 = 10;
 	data->in2 = 11;
@@ -53,6 +67,10 @@ void test_skeleton(void)
 	bss->in4 = 13;
 	rodata->in.in6 = 14;
 
+	rodata_dyn->in_dynarr_sz = 4;
+	for (i = 0; i < 4; i++)
+		rodata_dyn->in_dynarr[i] = i + 10;
+
 	err = test_skeleton__load(skel);
 	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
 		goto cleanup;
@@ -64,6 +82,10 @@ void test_skeleton(void)
 	CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL);
 	CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14);
 
+	ASSERT_EQ(rodata_dyn->in_dynarr_sz, 4, "in_dynarr_sz");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(rodata_dyn->in_dynarr[i], i + 10, "in_dynarr");
+
 	/* now set new values and attach to get them into outX variables */
 	data->in1 = 1;
 	data->in2 = 2;
@@ -73,6 +95,8 @@ void test_skeleton(void)
 	bss->in5.b = 6;
 	kcfg = skel->kconfig;
 
+	skel->data_read_mostly->read_mostly_var = 123;
+
 	err = test_skeleton__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
 		goto cleanup;
@@ -93,6 +117,11 @@ void test_skeleton(void)
 	CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2",
 	      "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION);
 
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(data_dyn->out_dynarr[i], i + 10, "out_dynarr");
+
+	ASSERT_EQ(skel->bss->out_mostly_var, 123, "out_mostly_var");
+
 	elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz);
 	ASSERT_OK_PTR(elf_bytes, "elf_bytes");
 	ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz");
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index 8fd1b4b29a0e..394ebfc3bbf3 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -33,7 +33,7 @@
 
 #define EXP_NO_BUF_RET 29
 
-void test_snprintf_positive(void)
+static void test_snprintf_positive(void)
 {
 	char exp_addr_out[] = EXP_ADDR_OUT;
 	char exp_sym_out[]  = EXP_SYM_OUT;
@@ -103,7 +103,7 @@ static int load_single_snprintf(char *fmt)
 	return ret;
 }
 
-void test_snprintf_negative(void)
+static void test_snprintf_negative(void)
 {
 	ASSERT_OK(load_single_snprintf("valid %d"), "valid usage");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
index 76e1f5fe18fa..dd41b826be30 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
@@ -6,7 +6,7 @@
 /* Demonstrate that bpf_snprintf_btf succeeds and that various data types
  * are formatted correctly.
  */
-void test_snprintf_btf(void)
+void serial_test_snprintf_btf(void)
 {
 	struct netif_receive_skb *skel;
 	struct netif_receive_skb__bss *bss;
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index 577d619fb07e..fae40db4d81f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -329,7 +329,7 @@ done:
 		close(listen_fd);
 }
 
-void test_sock_fields(void)
+void serial_test_sock_fields(void)
 {
 	struct bpf_link *egress_link = NULL, *ingress_link = NULL;
 	int parent_cg_fd = -1, child_cg_fd = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index d88bb65b74cc..2a9cb951bfd6 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -2002,7 +2002,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 	test_udp_unix_redir(skel, map, family);
 }
 
-void test_sockmap_listen(void)
+void serial_test_sockmap_listen(void)
 {
 	struct test_sockmap_listen *skel;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index e87bc4466d9a..4b18b73df10b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -176,6 +176,18 @@ static int netns_setup_namespaces(const char *verb)
 	return 0;
 }
 
+static void netns_setup_namespaces_nofail(const char *verb)
+{
+	const char * const *ns = namespaces;
+	char cmd[128];
+
+	while (*ns) {
+		snprintf(cmd, sizeof(cmd), "ip netns %s %s > /dev/null 2>&1", verb, *ns);
+		system(cmd);
+		ns++;
+	}
+}
+
 struct netns_setup_result {
 	int ifindex_veth_src_fwd;
 	int ifindex_veth_dst_fwd;
@@ -762,6 +774,8 @@ fail:
 
 static void *test_tc_redirect_run_tests(void *arg)
 {
+	netns_setup_namespaces_nofail("delete");
+
 	RUN_TEST(tc_redirect_peer);
 	RUN_TEST(tc_redirect_peer_l3);
 	RUN_TEST(tc_redirect_neigh);
@@ -769,7 +783,7 @@ static void *test_tc_redirect_run_tests(void *arg)
 	return NULL;
 }
 
-void test_tc_redirect(void)
+void serial_test_tc_redirect(void)
 {
 	pthread_t test_thread;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index d207e968e6b1..265b4fe33ec3 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -109,7 +109,7 @@ static int run_test(int cgroup_fd, int server_fd)
 		return -1;
 	}
 
-	map = bpf_map__next(NULL, obj);
+	map = bpf_object__next_map(obj, NULL);
 	map_fd = bpf_map__fd(map);
 
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index 0252f61d611a..97d8a6f84f4a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -43,7 +43,7 @@ static int process_sample(void *ctx, void *data, size_t len)
 void test_test_ima(void)
 {
 	char measured_dir_template[] = "/tmp/ima_measuredXXXXXX";
-	struct ring_buffer *ringbuf;
+	struct ring_buffer *ringbuf = NULL;
 	const char *measured_dir;
 	char cmd[256];
 
@@ -85,5 +85,6 @@ close_clean:
 	err = system(cmd);
 	CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno);
 close_prog:
+	ring_buffer__free(ringbuf);
 	ima__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 25f40e1b9967..0f4e49e622cd 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -39,7 +39,8 @@ static int timer(struct timer *timer_skel)
 	return 0;
 }
 
-void test_timer(void)
+/* TODO: use pid filtering */
+void serial_test_timer(void)
 {
 	struct timer *timer_skel = NULL;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index ced8f6cf347c..949a0617869d 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -52,7 +52,7 @@ static int timer_mim(struct timer_mim *timer_skel)
 	return 0;
 }
 
-void test_timer_mim(void)
+void serial_test_timer_mim(void)
 {
 	struct timer_mim_reject *timer_reject_skel = NULL;
 	libbpf_print_fn_t old_print_fn = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
index fb095e5cd9af..8652d0a46c87 100644
--- a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
+++ b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
-void test_tp_attach_query(void)
+void serial_test_tp_attach_query(void)
 {
 	const int num_progs = 3;
 	int i, j, bytes, efd, err, prog_fd[num_progs], pmu_fd[num_progs];
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index e47835f0a674..cade7f12315f 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -8,29 +8,29 @@
 #define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"testing,testing"
 
-void test_trace_printk(void)
+void serial_test_trace_printk(void)
 {
+	struct trace_printk_lskel__bss *bss;
 	int err = 0, iter = 0, found = 0;
-	struct trace_printk__bss *bss;
-	struct trace_printk *skel;
+	struct trace_printk_lskel *skel;
 	char *buf = NULL;
 	FILE *fp = NULL;
 	size_t buflen;
 
-	skel = trace_printk__open();
+	skel = trace_printk_lskel__open();
 	if (!ASSERT_OK_PTR(skel, "trace_printk__open"))
 		return;
 
 	ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]");
 	skel->rodata->fmt[0] = 't';
 
-	err = trace_printk__load(skel);
+	err = trace_printk_lskel__load(skel);
 	if (!ASSERT_OK(err, "trace_printk__load"))
 		goto cleanup;
 
 	bss = skel->bss;
 
-	err = trace_printk__attach(skel);
+	err = trace_printk_lskel__attach(skel);
 	if (!ASSERT_OK(err, "trace_printk__attach"))
 		goto cleanup;
 
@@ -43,7 +43,7 @@ void test_trace_printk(void)
 
 	/* wait for tracepoint to trigger */
 	usleep(1);
-	trace_printk__detach(skel);
+	trace_printk_lskel__detach(skel);
 
 	if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran"))
 		goto cleanup;
@@ -65,7 +65,7 @@ void test_trace_printk(void)
 		goto cleanup;
 
 cleanup:
-	trace_printk__destroy(skel);
+	trace_printk_lskel__destroy(skel);
 	free(buf);
 	if (fp)
 		fclose(fp);
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
index 61a24e62e1a0..7a4e313e8558 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
@@ -8,22 +8,22 @@
 #define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"1,2,3,4,5,6,7,8,9,10"
 
-void test_trace_vprintk(void)
+void serial_test_trace_vprintk(void)
 {
+	struct trace_vprintk_lskel__bss *bss;
 	int err = 0, iter = 0, found = 0;
-	struct trace_vprintk__bss *bss;
-	struct trace_vprintk *skel;
+	struct trace_vprintk_lskel *skel;
 	char *buf = NULL;
 	FILE *fp = NULL;
 	size_t buflen;
 
-	skel = trace_vprintk__open_and_load();
+	skel = trace_vprintk_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
 		goto cleanup;
 
 	bss = skel->bss;
 
-	err = trace_vprintk__attach(skel);
+	err = trace_vprintk_lskel__attach(skel);
 	if (!ASSERT_OK(err, "trace_vprintk__attach"))
 		goto cleanup;
 
@@ -36,7 +36,7 @@ void test_trace_vprintk(void)
 
 	/* wait for tracepoint to trigger */
 	usleep(1);
-	trace_vprintk__detach(skel);
+	trace_vprintk_lskel__detach(skel);
 
 	if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran"))
 		goto cleanup;
@@ -61,7 +61,7 @@ void test_trace_vprintk(void)
 		goto cleanup;
 
 cleanup:
-	trace_vprintk__destroy(skel);
+	trace_vprintk_lskel__destroy(skel);
 	free(buf);
 	if (fp)
 		fclose(fp);
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index d7f5a931d7f3..fc146671b20a 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -41,7 +41,8 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
 	return bpf_program__attach_trace(prog);
 }
 
-void test_trampoline_count(void)
+/* TODO: use different target function to run in concurrent mode */
+void serial_test_trampoline_count(void)
 {
 	const char *fentry_name = "fentry/__set_task_comm";
 	const char *fexit_name = "fexit/__set_task_comm";
diff --git a/tools/testing/selftests/bpf/prog_tests/verif_stats.c b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
new file mode 100644
index 000000000000..a47e7c0e1ffd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+
+#include "trace_vprintk.lskel.h"
+
+void test_verif_stats(void)
+{
+	__u32 len = sizeof(struct bpf_prog_info);
+	struct trace_vprintk_lskel *skel;
+	struct bpf_prog_info info = {};
+	int err;
+
+	skel = trace_vprintk_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
+		goto cleanup;
+
+	err = bpf_obj_get_info_by_fd(skel->progs.sys_enter.prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+		goto cleanup;
+
+	if (!ASSERT_GT(info.verified_insns, 0, "verified_insns"))
+		goto cleanup;
+
+cleanup:
+	trace_vprintk_lskel__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index d5c98f2cb12f..f529e3c923ae 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-void test_xdp_adjust_tail_shrink(void)
+static void test_xdp_adjust_tail_shrink(void)
 {
 	const char *file = "./test_xdp_adjust_tail_shrink.o";
 	__u32 duration, retval, size, expect_sz;
@@ -30,7 +30,7 @@ void test_xdp_adjust_tail_shrink(void)
 	bpf_object__close(obj);
 }
 
-void test_xdp_adjust_tail_grow(void)
+static void test_xdp_adjust_tail_grow(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.o";
 	struct bpf_object *obj;
@@ -58,7 +58,7 @@ void test_xdp_adjust_tail_grow(void)
 	bpf_object__close(obj);
 }
 
-void test_xdp_adjust_tail_grow2(void)
+static void test_xdp_adjust_tail_grow2(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.o";
 	char buf[4096]; /* avoid segfault: large buf to hold grow results */
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index 15ef3531483e..4c4057262cd8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -4,7 +4,7 @@
 #define IFINDEX_LO 1
 #define XDP_FLAGS_REPLACE		(1U << 4)
 
-void test_xdp_attach(void)
+void serial_test_xdp_attach(void)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, len;
 	struct bpf_object *obj1, *obj2, *obj3;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index ad3ba81b4048..faa22b84f2ee 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -519,7 +519,7 @@ static struct bond_test_case bond_test_cases[] = {
 	{ "xdp_bonding_xor_layer34", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER34, },
 };
 
-void test_xdp_bonding(void)
+void serial_test_xdp_bonding(void)
 {
 	libbpf_print_fn_t old_print_fn;
 	struct skeletons skeletons = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index 8755effd80b0..fd812bd43600 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -7,7 +7,7 @@
 
 #define IFINDEX_LO	1
 
-void test_xdp_cpumap_attach(void)
+void serial_test_xdp_cpumap_attach(void)
 {
 	struct test_xdp_with_cpumap_helpers *skel;
 	struct bpf_prog_info info = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index c72af030ff10..3079d5568f8f 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -8,7 +8,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_with_devmap_helpers(void)
+static void test_xdp_with_devmap_helpers(void)
 {
 	struct test_xdp_with_devmap_helpers *skel;
 	struct bpf_prog_info info = {};
@@ -60,7 +60,7 @@ out_close:
 	test_xdp_with_devmap_helpers__destroy(skel);
 }
 
-void test_neg_xdp_devmap_helpers(void)
+static void test_neg_xdp_devmap_helpers(void)
 {
 	struct test_xdp_devmap_helpers *skel;
 
@@ -72,7 +72,7 @@ void test_neg_xdp_devmap_helpers(void)
 }
 
 
-void test_xdp_devmap_attach(void)
+void serial_test_xdp_devmap_attach(void)
 {
 	if (test__start_subtest("DEVMAP with programs in entries"))
 		test_xdp_with_devmap_helpers();
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
index d2d7a283d72f..4e2a4fd56f67 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -4,7 +4,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_info(void)
+void serial_test_xdp_info(void)
 {
 	__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
 	const char *file = "./xdp_dummy.o";
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 46eed0a33c23..983ab0b47d30 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -6,7 +6,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_link(void)
+void serial_test_xdp_link(void)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
 	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);