Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Add WireGuard

 2) Add HE and TWT support to ath11k driver, from John Crispin.

 3) Add ESP in TCP encapsulation support, from Sabrina Dubroca.

 4) Add variable window congestion control to TIPC, from Jon Maloy.

 5) Add BCM84881 PHY driver, from Russell King.

 6) Start adding netlink support for ethtool operations, from Michal
    Kubecek.

 7) Add XDP drop and TX action support to ena driver, from Sameeh
    Jubran.

 8) Add new ipv4 route notifications so that mlxsw driver does not have
    to handle identical routes itself. From Ido Schimmel.

 9) Add BPF dynamic program extensions, from Alexei Starovoitov.

10) Support RX and TX timestamping in igc, from Vinicius Costa Gomes.

11) Add support for macsec HW offloading, from Antoine Tenart.

12) Add initial support for MPTCP protocol, from Christoph Paasch,
    Matthieu Baerts, Florian Westphal, Peter Krystad, and many others.

13) Add Octeontx2 PF support, from Sunil Goutham, Geetha sowjanya, Linu
    Cherian, and others.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1469 commits)
  net: phy: add default ARCH_BCM_IPROC for MDIO_BCM_IPROC
  udp: segment looped gso packets correctly
  netem: change mailing list
  qed: FW 8.42.2.0 debug features
  qed: rt init valid initialization changed
  qed: Debug feature: ilt and mdump
  qed: FW 8.42.2.0 Add fw overlay feature
  qed: FW 8.42.2.0 HSI changes
  qed: FW 8.42.2.0 iscsi/fcoe changes
  qed: Add abstraction for different hsi values per chip
  qed: FW 8.42.2.0 Additional ll2 type
  qed: Use dmae to write to widebus registers in fw_funcs
  qed: FW 8.42.2.0 Parser offsets modified
  qed: FW 8.42.2.0 Queue Manager changes
  qed: FW 8.42.2.0 Expose new registers and change windows
  qed: FW 8.42.2.0 Internal ram offsets modifications
  MAINTAINERS: Add entry for Marvell OcteonTX2 Physical Function driver
  Documentation: net: octeontx2: Add RVU HW and drivers overview
  octeontx2-pf: ethtool RSS config support
  octeontx2-pf: Add basic ethtool support
  ...

28 files changed, 2490 insertions, 478 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index a83111a32d4a..a0ee87c8e1ea 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -1,26 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
-
-#define EMBED_FILE(NAME, PATH)						    \
-asm (									    \
-"      .pushsection \".rodata\", \"a\", @progbits              \n"	    \
-"      .global "#NAME"_data                                    \n"	    \
-#NAME"_data:                                                   \n"	    \
-"      .incbin \"" PATH "\"                                    \n"	    \
-#NAME"_data_end:                                               \n"	    \
-"      .global "#NAME"_size                                    \n"	    \
-"      .type "#NAME"_size, @object                             \n"	    \
-"      .size "#NAME"_size, 4                                   \n"	    \
-"      .align 4,                                               \n"	    \
-#NAME"_size:                                                   \n"	    \
-"      .int "#NAME"_data_end - "#NAME"_data                    \n"	    \
-"      .popsection                                             \n"	    \
-);									    \
-extern char NAME##_data[];						    \
-extern int NAME##_size;
+#include "test_attach_probe.skel.h"
 
 ssize_t get_base_addr() {
-	size_t start;
+	size_t start, offset;
 	char buf[256];
 	FILE *f;
 
@@ -28,10 +11,11 @@ ssize_t get_base_addr() {
 	if (!f)
 		return -errno;
 
-	while (fscanf(f, "%zx-%*x %s %*s\n", &start, buf) == 2) {
+	while (fscanf(f, "%zx-%*x %s %zx %*[^\n]\n",
+		      &start, buf, &offset) == 3) {
 		if (strcmp(buf, "r-xp") == 0) {
 			fclose(f);
-			return start;
+			return start - offset;
 		}
 	}
 
@@ -39,30 +23,12 @@ ssize_t get_base_addr() {
 	return -EINVAL;
 }
 
-EMBED_FILE(probe, "test_attach_probe.o");
-
 void test_attach_probe(void)
 {
-	const char *kprobe_name = "kprobe/sys_nanosleep";
-	const char *kretprobe_name = "kretprobe/sys_nanosleep";
-	const char *uprobe_name = "uprobe/trigger_func";
-	const char *uretprobe_name = "uretprobe/trigger_func";
-	const int kprobe_idx = 0, kretprobe_idx = 1;
-	const int uprobe_idx = 2, uretprobe_idx = 3;
-	const char *obj_name = "attach_probe";
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, open_opts,
-		.object_name = obj_name,
-		.relaxed_maps = true,
-	);
-	struct bpf_program *kprobe_prog, *kretprobe_prog;
-	struct bpf_program *uprobe_prog, *uretprobe_prog;
-	struct bpf_object *obj;
-	int err, duration = 0, res;
-	struct bpf_link *kprobe_link = NULL;
-	struct bpf_link *kretprobe_link = NULL;
-	struct bpf_link *uprobe_link = NULL;
-	struct bpf_link *uretprobe_link = NULL;
-	int results_map_fd;
+	int duration = 0;
+	struct bpf_link *kprobe_link, *kretprobe_link;
+	struct bpf_link *uprobe_link, *uretprobe_link;
+	struct test_attach_probe* skel;
 	size_t uprobe_offset;
 	ssize_t base_addr;
 
@@ -72,123 +38,68 @@ void test_attach_probe(void)
 		return;
 	uprobe_offset = (size_t)&get_base_addr - base_addr;
 
-	/* open object */
-	obj = bpf_object__open_mem(probe_data, probe_size, &open_opts);
-	if (CHECK(IS_ERR(obj), "obj_open_mem", "err %ld\n", PTR_ERR(obj)))
+	skel = test_attach_probe__open_and_load();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
 		return;
-
-	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
-		  "wrong obj name '%s', expected '%s'\n",
-		  bpf_object__name(obj), obj_name))
+	if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n"))
 		goto cleanup;
 
-	kprobe_prog = bpf_object__find_program_by_title(obj, kprobe_name);
-	if (CHECK(!kprobe_prog, "find_probe",
-		  "prog '%s' not found\n", kprobe_name))
-		goto cleanup;
-	kretprobe_prog = bpf_object__find_program_by_title(obj, kretprobe_name);
-	if (CHECK(!kretprobe_prog, "find_probe",
-		  "prog '%s' not found\n", kretprobe_name))
-		goto cleanup;
-	uprobe_prog = bpf_object__find_program_by_title(obj, uprobe_name);
-	if (CHECK(!uprobe_prog, "find_probe",
-		  "prog '%s' not found\n", uprobe_name))
-		goto cleanup;
-	uretprobe_prog = bpf_object__find_program_by_title(obj, uretprobe_name);
-	if (CHECK(!uretprobe_prog, "find_probe",
-		  "prog '%s' not found\n", uretprobe_name))
-		goto cleanup;
-
-	/* create maps && load programs */
-	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "err %d\n", err))
-		goto cleanup;
-
-	/* load maps */
-	results_map_fd = bpf_find_map(__func__, obj, "results_map");
-	if (CHECK(results_map_fd < 0, "find_results_map",
-		  "err %d\n", results_map_fd))
-		goto cleanup;
-
-	kprobe_link = bpf_program__attach_kprobe(kprobe_prog,
+	kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe,
 						 false /* retprobe */,
 						 SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
-		  "err %ld\n", PTR_ERR(kprobe_link))) {
-		kprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(kprobe_link)))
 		goto cleanup;
-	}
-	kretprobe_link = bpf_program__attach_kprobe(kretprobe_prog,
+	skel->links.handle_kprobe = kprobe_link;
+
+	kretprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kretprobe,
 						    true /* retprobe */,
 						    SYS_NANOSLEEP_KPROBE_NAME);
 	if (CHECK(IS_ERR(kretprobe_link), "attach_kretprobe",
-		  "err %ld\n", PTR_ERR(kretprobe_link))) {
-		kretprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(kretprobe_link)))
 		goto cleanup;
-	}
-	uprobe_link = bpf_program__attach_uprobe(uprobe_prog,
+	skel->links.handle_kretprobe = kretprobe_link;
+
+	uprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uprobe,
 						 false /* retprobe */,
 						 0 /* self pid */,
 						 "/proc/self/exe",
 						 uprobe_offset);
 	if (CHECK(IS_ERR(uprobe_link), "attach_uprobe",
-		  "err %ld\n", PTR_ERR(uprobe_link))) {
-		uprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(uprobe_link)))
 		goto cleanup;
-	}
-	uretprobe_link = bpf_program__attach_uprobe(uretprobe_prog,
+	skel->links.handle_uprobe = uprobe_link;
+
+	uretprobe_link = bpf_program__attach_uprobe(skel->progs.handle_uretprobe,
 						    true /* retprobe */,
 						    -1 /* any pid */,
 						    "/proc/self/exe",
 						    uprobe_offset);
 	if (CHECK(IS_ERR(uretprobe_link), "attach_uretprobe",
-		  "err %ld\n", PTR_ERR(uretprobe_link))) {
-		uretprobe_link = NULL;
+		  "err %ld\n", PTR_ERR(uretprobe_link)))
 		goto cleanup;
-	}
+	skel->links.handle_uretprobe = uretprobe_link;
 
 	/* trigger & validate kprobe && kretprobe */
 	usleep(1);
 
-	err = bpf_map_lookup_elem(results_map_fd, &kprobe_idx, &res);
-	if (CHECK(err, "get_kprobe_res",
-		  "failed to get kprobe res: %d\n", err))
+	if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res",
+		  "wrong kprobe res: %d\n", skel->bss->kprobe_res))
 		goto cleanup;
-	if (CHECK(res != kprobe_idx + 1, "check_kprobe_res",
-		  "wrong kprobe res: %d\n", res))
-		goto cleanup;
-
-	err = bpf_map_lookup_elem(results_map_fd, &kretprobe_idx, &res);
-	if (CHECK(err, "get_kretprobe_res",
-		  "failed to get kretprobe res: %d\n", err))
-		goto cleanup;
-	if (CHECK(res != kretprobe_idx + 1, "check_kretprobe_res",
-		  "wrong kretprobe res: %d\n", res))
+	if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res",
+		  "wrong kretprobe res: %d\n", skel->bss->kretprobe_res))
 		goto cleanup;
 
 	/* trigger & validate uprobe & uretprobe */
 	get_base_addr();
 
-	err = bpf_map_lookup_elem(results_map_fd, &uprobe_idx, &res);
-	if (CHECK(err, "get_uprobe_res",
-		  "failed to get uprobe res: %d\n", err))
-		goto cleanup;
-	if (CHECK(res != uprobe_idx + 1, "check_uprobe_res",
-		  "wrong uprobe res: %d\n", res))
-		goto cleanup;
-
-	err = bpf_map_lookup_elem(results_map_fd, &uretprobe_idx, &res);
-	if (CHECK(err, "get_uretprobe_res",
-		  "failed to get uretprobe res: %d\n", err))
+	if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res",
+		  "wrong uprobe res: %d\n", skel->bss->uprobe_res))
 		goto cleanup;
-	if (CHECK(res != uretprobe_idx + 1, "check_uretprobe_res",
-		  "wrong uretprobe res: %d\n", res))
+	if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res",
+		  "wrong uretprobe res: %d\n", skel->bss->uretprobe_res))
 		goto cleanup;
 
 cleanup:
-	bpf_link__destroy(kprobe_link);
-	bpf_link__destroy(kretprobe_link);
-	bpf_link__destroy(uprobe_link);
-	bpf_link__destroy(uretprobe_link);
-	bpf_object__close(obj);
+	test_attach_probe__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
new file mode 100644
index 000000000000..8482bbc67eec
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <linux/err.h>
+#include <test_progs.h>
+#include "bpf_dctcp.skel.h"
+#include "bpf_cubic.skel.h"
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+static const unsigned int total_bytes = 10 * 1024 * 1024;
+static const struct timeval timeo_sec = { .tv_sec = 10 };
+static const size_t timeo_optlen = sizeof(timeo_sec);
+static int stop, duration;
+
+static int settimeo(int fd)
+{
+	int err;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_RCVTIMEO, &timeo_sec,
+			 timeo_optlen);
+	if (CHECK(err == -1, "setsockopt(fd, SO_RCVTIMEO)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	err = setsockopt(fd, SOL_SOCKET, SO_SNDTIMEO, &timeo_sec,
+			 timeo_optlen);
+	if (CHECK(err == -1, "setsockopt(fd, SO_SNDTIMEO)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	return 0;
+}
+
+static int settcpca(int fd, const char *tcp_ca)
+{
+	int err;
+
+	err = setsockopt(fd, IPPROTO_TCP, TCP_CONGESTION, tcp_ca, strlen(tcp_ca));
+	if (CHECK(err == -1, "setsockopt(fd, TCP_CONGESTION)", "errno:%d\n",
+		  errno))
+		return -1;
+
+	return 0;
+}
+
+static void *server(void *arg)
+{
+	int lfd = (int)(long)arg, err = 0, fd;
+	ssize_t nr_sent = 0, bytes = 0;
+	char batch[1500];
+
+	fd = accept(lfd, NULL, NULL);
+	while (fd == -1) {
+		if (errno == EINTR)
+			continue;
+		err = -errno;
+		goto done;
+	}
+
+	if (settimeo(fd)) {
+		err = -errno;
+		goto done;
+	}
+
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_sent = send(fd, &batch,
+			       min(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_sent == -1 && errno == EINTR)
+			continue;
+		if (nr_sent == -1) {
+			err = -errno;
+			break;
+		}
+		bytes += nr_sent;
+	}
+
+	CHECK(bytes != total_bytes, "send", "%zd != %u nr_sent:%zd errno:%d\n",
+	      bytes, total_bytes, nr_sent, errno);
+
+done:
+	if (fd != -1)
+		close(fd);
+	if (err) {
+		WRITE_ONCE(stop, 1);
+		return ERR_PTR(err);
+	}
+	return NULL;
+}
+
+static void do_test(const char *tcp_ca)
+{
+	struct sockaddr_in6 sa6 = {};
+	ssize_t nr_recv = 0, bytes = 0;
+	int lfd = -1, fd = -1;
+	pthread_t srv_thread;
+	socklen_t addrlen = sizeof(sa6);
+	void *thread_ret;
+	char batch[1500];
+	int err;
+
+	WRITE_ONCE(stop, 0);
+
+	lfd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(lfd == -1, "socket", "errno:%d\n", errno))
+		return;
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (CHECK(fd == -1, "socket", "errno:%d\n", errno)) {
+		close(lfd);
+		return;
+	}
+
+	if (settcpca(lfd, tcp_ca) || settcpca(fd, tcp_ca) ||
+	    settimeo(lfd) || settimeo(fd))
+		goto done;
+
+	/* bind, listen and start server thread to accept */
+	sa6.sin6_family = AF_INET6;
+	sa6.sin6_addr = in6addr_loopback;
+	err = bind(lfd, (struct sockaddr *)&sa6, addrlen);
+	if (CHECK(err == -1, "bind", "errno:%d\n", errno))
+		goto done;
+	err = getsockname(lfd, (struct sockaddr *)&sa6, &addrlen);
+	if (CHECK(err == -1, "getsockname", "errno:%d\n", errno))
+		goto done;
+	err = listen(lfd, 1);
+	if (CHECK(err == -1, "listen", "errno:%d\n", errno))
+		goto done;
+	err = pthread_create(&srv_thread, NULL, server, (void *)(long)lfd);
+	if (CHECK(err != 0, "pthread_create", "err:%d\n", err))
+		goto done;
+
+	/* connect to server */
+	err = connect(fd, (struct sockaddr *)&sa6, addrlen);
+	if (CHECK(err == -1, "connect", "errno:%d\n", errno))
+		goto wait_thread;
+
+	/* recv total_bytes */
+	while (bytes < total_bytes && !READ_ONCE(stop)) {
+		nr_recv = recv(fd, &batch,
+			       min(total_bytes - bytes, sizeof(batch)), 0);
+		if (nr_recv == -1 && errno == EINTR)
+			continue;
+		if (nr_recv == -1)
+			break;
+		bytes += nr_recv;
+	}
+
+	CHECK(bytes != total_bytes, "recv", "%zd != %u nr_recv:%zd errno:%d\n",
+	      bytes, total_bytes, nr_recv, errno);
+
+wait_thread:
+	WRITE_ONCE(stop, 1);
+	pthread_join(srv_thread, &thread_ret);
+	CHECK(IS_ERR(thread_ret), "pthread_join", "thread_ret:%ld",
+	      PTR_ERR(thread_ret));
+done:
+	close(lfd);
+	close(fd);
+}
+
+static void test_cubic(void)
+{
+	struct bpf_cubic *cubic_skel;
+	struct bpf_link *link;
+
+	cubic_skel = bpf_cubic__open_and_load();
+	if (CHECK(!cubic_skel, "bpf_cubic__open_and_load", "failed\n"))
+		return;
+
+	link = bpf_map__attach_struct_ops(cubic_skel->maps.cubic);
+	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+		  PTR_ERR(link))) {
+		bpf_cubic__destroy(cubic_skel);
+		return;
+	}
+
+	do_test("bpf_cubic");
+
+	bpf_link__destroy(link);
+	bpf_cubic__destroy(cubic_skel);
+}
+
+static void test_dctcp(void)
+{
+	struct bpf_dctcp *dctcp_skel;
+	struct bpf_link *link;
+
+	dctcp_skel = bpf_dctcp__open_and_load();
+	if (CHECK(!dctcp_skel, "bpf_dctcp__open_and_load", "failed\n"))
+		return;
+
+	link = bpf_map__attach_struct_ops(dctcp_skel->maps.dctcp);
+	if (CHECK(IS_ERR(link), "bpf_map__attach_struct_ops", "err:%ld\n",
+		  PTR_ERR(link))) {
+		bpf_dctcp__destroy(dctcp_skel);
+		return;
+	}
+
+	do_test("bpf_dctcp");
+
+	bpf_link__destroy(link);
+	bpf_dctcp__destroy(dctcp_skel);
+}
+
+void test_bpf_tcp_ca(void)
+{
+	if (test__start_subtest("dctcp"))
+		test_dctcp();
+	if (test__start_subtest("cubic"))
+		test_cubic();
+}
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 9486c13af6b2..e9f2f12ba06b 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -48,6 +48,8 @@ void test_bpf_verif_scale(void)
 		{ "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 },
+
 		/* full unroll by llvm */
 		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
 		{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
new file mode 100644
index 000000000000..5b13f2c6c402
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int prog_load(void)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, 1), /* r0 = 1 */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+void test_cgroup_attach_autodetach(void)
+{
+	__u32 duration = 0, prog_cnt = 4, attach_flags;
+	int allow_prog[2] = {-1};
+	__u32 prog_ids[2] = {0};
+	void *ptr = NULL;
+	int cg = 0, i;
+	int attempts;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load();
+		if (CHECK(allow_prog[i] < 0, "prog_load",
+			  "verifier output:\n%s\n-------\n", bpf_log_buf))
+			goto err;
+	}
+
+	if (CHECK_FAIL(setup_cgroup_environment()))
+		goto err;
+
+	/* create a cgroup, attach two programs and remember their ids */
+	cg = create_and_get_cgroup("/cg_autodetach");
+	if (CHECK_FAIL(cg < 0))
+		goto err;
+
+	if (CHECK_FAIL(join_cgroup("/cg_autodetach")))
+		goto err;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (CHECK(bpf_prog_attach(allow_prog[i], cg,
+					  BPF_CGROUP_INET_EGRESS,
+					  BPF_F_ALLOW_MULTI),
+			  "prog_attach", "prog[%d], errno=%d\n", i, errno))
+			goto err;
+
+	/* make sure that programs are attached and run some traffic */
+	if (CHECK(bpf_prog_query(cg, BPF_CGROUP_INET_EGRESS, 0, &attach_flags,
+				 prog_ids, &prog_cnt),
+		  "prog_query", "errno=%d\n", errno))
+		goto err;
+	if (CHECK_FAIL(system(PING_CMD)))
+		goto err;
+
+	/* allocate some memory (4Mb) to pin the original cgroup */
+	ptr = malloc(4 * (1 << 20));
+	if (CHECK_FAIL(!ptr))
+		goto err;
+
+	/* close programs and cgroup fd */
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		close(allow_prog[i]);
+		allow_prog[i] = -1;
+	}
+
+	close(cg);
+	cg = 0;
+
+	/* leave the cgroup and remove it. don't detach programs */
+	cleanup_cgroup_environment();
+
+	/* wait for the asynchronous auto-detachment.
+	 * wait for no more than 5 sec and give up.
+	 */
+	for (i = 0; i < ARRAY_SIZE(prog_ids); i++) {
+		for (attempts = 5; attempts >= 0; attempts--) {
+			int fd = bpf_prog_get_fd_by_id(prog_ids[i]);
+
+			if (fd < 0)
+				break;
+
+			/* don't leave the fd open */
+			close(fd);
+
+			if (CHECK_FAIL(!attempts))
+				goto err;
+
+			sleep(1);
+		}
+	}
+
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] >= 0)
+			close(allow_prog[i]);
+	if (cg)
+		close(cg);
+	free(ptr);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
new file mode 100644
index 000000000000..2ff21dbce179
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -0,0 +1,285 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int map_fd = -1;
+
+static int prog_load_cnt(int verdict, int val)
+{
+	int cgroup_storage_fd, percpu_cgroup_storage_fd;
+
+	if (map_fd < 0)
+		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
+	if (map_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	percpu_cgroup_storage_fd = bpf_create_map(
+		BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+		sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (percpu_cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
+	struct bpf_insn prog[] = {
+		BPF_MOV32_IMM(BPF_REG_0, 0),
+		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+		BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+		BPF_LD_MAP_FD(BPF_REG_1, map_fd),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+
+		BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_MOV64_IMM(BPF_REG_1, val),
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
+
+		BPF_LD_MAP_FD(BPF_REG_1, percpu_cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1),
+		BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0),
+
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+	int ret;
+
+	ret = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+
+	close(cgroup_storage_fd);
+	return ret;
+}
+
+void 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;
+	DECLARE_LIBBPF_OPTS(bpf_prog_attach_opts, attach_opts);
+	int allow_prog[7] = {-1};
+	unsigned long long value;
+	__u32 duration = 0;
+	int i = 0;
+
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++) {
+		allow_prog[i] = prog_load_cnt(1, 1 << i);
+		if (CHECK(allow_prog[i] < 0, "prog_load",
+			  "verifier output:\n%s\n-------\n", bpf_log_buf))
+			goto err;
+	}
+
+	if (CHECK_FAIL(setup_cgroup_environment()))
+		goto err;
+
+	cg1 = create_and_get_cgroup("/cg1");
+	if (CHECK_FAIL(cg1 < 0))
+		goto err;
+	cg2 = create_and_get_cgroup("/cg1/cg2");
+	if (CHECK_FAIL(cg2 < 0))
+		goto err;
+	cg3 = create_and_get_cgroup("/cg1/cg2/cg3");
+	if (CHECK_FAIL(cg3 < 0))
+		goto err;
+	cg4 = create_and_get_cgroup("/cg1/cg2/cg3/cg4");
+	if (CHECK_FAIL(cg4 < 0))
+		goto err;
+	cg5 = create_and_get_cgroup("/cg1/cg2/cg3/cg4/cg5");
+	if (CHECK_FAIL(cg5 < 0))
+		goto err;
+
+	if (CHECK_FAIL(join_cgroup("/cg1/cg2/cg3/cg4/cg5")))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog0_attach_to_cg1_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog[0], cg1, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_MULTI),
+		  "fail_same_prog_attach_to_cg1", "unexpected success\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[1], cg1, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog1_attach_to_cg1_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[2], cg2, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog2_attach_to_cg2_override", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_MULTI),
+		  "prog3_attach_to_cg3_multi", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[4], cg4, BPF_CGROUP_INET_EGRESS,
+			    BPF_F_ALLOW_OVERRIDE),
+		  "prog4_attach_to_cg4_override", "errno=%d\n", errno))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog[5], cg5, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog5_attach_to_cg5_none", "errno=%d\n", errno))
+		goto err;
+
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 1 + 2 + 8 + 32);
+
+	/* query the number of effective progs in cg5 */
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, NULL, NULL, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 4);
+	/* retrieve prog_ids of effective progs in cg5 */
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 4);
+	CHECK_FAIL(attach_flags != 0);
+	saved_prog_id = prog_ids[0];
+	/* check enospc handling */
+	prog_ids[0] = 0;
+	prog_cnt = 2;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt) != -1);
+	CHECK_FAIL(errno != ENOSPC);
+	CHECK_FAIL(prog_cnt != 4);
+	/* check that prog_ids are returned even when buffer is too small */
+	CHECK_FAIL(prog_ids[0] != saved_prog_id);
+	/* retrieve prog_id of single attached prog in cg5 */
+	prog_ids[0] = 0;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 1);
+	CHECK_FAIL(prog_ids[0] != saved_prog_id);
+
+	/* detach bottom program and ping again */
+	if (CHECK(bpf_prog_detach2(-1, cg5, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_from_cg5", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 1 + 2 + 8 + 16);
+
+	/* test replace */
+
+	attach_opts.flags = BPF_F_ALLOW_OVERRIDE | BPF_F_REPLACE;
+	attach_opts.replace_prog_fd = allow_prog[0];
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_override", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EINVAL);
+
+	attach_opts.flags = BPF_F_REPLACE;
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_no_multi", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EINVAL);
+
+	attach_opts.flags = BPF_F_ALLOW_MULTI | BPF_F_REPLACE;
+	attach_opts.replace_prog_fd = -1;
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_bad_fd", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != EBADF);
+
+	/* replacing a program that is not attached to cgroup should fail  */
+	attach_opts.replace_prog_fd = allow_prog[3];
+	if (CHECK(!bpf_prog_attach_xattr(allow_prog[6], cg1,
+					 BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "fail_prog_replace_no_ent", "unexpected success\n"))
+		goto err;
+	CHECK_FAIL(errno != ENOENT);
+
+	/* replace 1st from the top program */
+	attach_opts.replace_prog_fd = allow_prog[0];
+	if (CHECK(bpf_prog_attach_xattr(allow_prog[6], cg1,
+					BPF_CGROUP_INET_EGRESS, &attach_opts),
+		  "prog_replace", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 8 + 16);
+
+	/* detach 3rd from bottom program and ping again */
+	if (CHECK(!bpf_prog_detach2(0, cg3, BPF_CGROUP_INET_EGRESS),
+		  "fail_prog_detach_from_cg3", "unexpected success\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_detach2(allow_prog[3], cg3, BPF_CGROUP_INET_EGRESS),
+		  "prog3_detach_from_cg3", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 16);
+
+	/* detach 2nd from bottom program and ping again */
+	if (CHECK(bpf_prog_detach2(-1, cg4, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_from_cg4", "errno=%d\n", errno))
+		goto err;
+
+	value = 0;
+	CHECK_FAIL(bpf_map_update_elem(map_fd, &key, &value, 0));
+	CHECK_FAIL(system(PING_CMD));
+	CHECK_FAIL(bpf_map_lookup_elem(map_fd, &key, &value));
+	CHECK_FAIL(value != 64 + 2 + 4);
+
+	prog_cnt = 4;
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_QUERY_EFFECTIVE, &attach_flags,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 3);
+	CHECK_FAIL(attach_flags != 0);
+	CHECK_FAIL(bpf_prog_query(cg5, BPF_CGROUP_INET_EGRESS, 0, NULL,
+				  prog_ids, &prog_cnt));
+	CHECK_FAIL(prog_cnt != 0);
+
+err:
+	for (i = 0; i < ARRAY_SIZE(allow_prog); i++)
+		if (allow_prog[i] >= 0)
+			close(allow_prog[i]);
+	close(cg1);
+	close(cg2);
+	close(cg3);
+	close(cg4);
+	close(cg5);
+	cleanup_cgroup_environment();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
new file mode 100644
index 000000000000..9d8cb48b99de
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#include "cgroup_helpers.h"
+
+#define FOO		"/foo"
+#define BAR		"/foo/bar/"
+#define PING_CMD	"ping -q -c1 -w1 127.0.0.1 > /dev/null"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+static int prog_load(int verdict)
+{
+	struct bpf_insn prog[] = {
+		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+
+	return bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+			       prog, insns_cnt, "GPL", 0,
+			       bpf_log_buf, BPF_LOG_BUF_SIZE);
+}
+
+void test_cgroup_attach_override(void)
+{
+	int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1;
+	__u32 duration = 0;
+
+	allow_prog = prog_load(1);
+	if (CHECK(allow_prog < 0, "prog_load_allow",
+		  "verifier output:\n%s\n-------\n", bpf_log_buf))
+		goto err;
+
+	drop_prog = prog_load(0);
+	if (CHECK(drop_prog < 0, "prog_load_drop",
+		  "verifier output:\n%s\n-------\n", bpf_log_buf))
+		goto err;
+
+	foo = test__join_cgroup(FOO);
+	if (CHECK(foo < 0, "cgroup_join_foo", "cgroup setup failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_drop_foo_override",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	bar = test__join_cgroup(BAR);
+	if (CHECK(bar < 0, "cgroup_join_bar", "cgroup setup failed\n"))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_bar",
+		  "detach prog from %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!system(PING_CMD), "ping_fail",
+		  "ping unexpectedly succeeded\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_foo",
+		  "detach prog from %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(system(PING_CMD), "ping_ok", "ping failed\n"))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				  BPF_F_ALLOW_OVERRIDE),
+		  "prog_attach_allow_bar_override",
+		  "attach prog to %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0),
+		  "fail_prog_attach_allow_bar_none",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(bpf_prog_detach(bar, BPF_CGROUP_INET_EGRESS),
+		  "prog_detach_bar",
+		  "detach prog from %s failed, errno=%d\n", BAR, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_detach(foo, BPF_CGROUP_INET_EGRESS),
+		  "fail_prog_detach_foo",
+		  "double detach from %s unexpectedly succeeded\n", FOO))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog_attach_allow_foo_none",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS, 0),
+		  "fail_prog_attach_allow_bar_none",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, bar, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_OVERRIDE),
+		  "fail_prog_attach_allow_bar_override",
+		  "attach prog to %s unexpectedly succeeded\n", BAR))
+		goto err;
+
+	if (CHECK(!bpf_prog_attach(allow_prog, foo, BPF_CGROUP_INET_EGRESS,
+				   BPF_F_ALLOW_OVERRIDE),
+		  "fail_prog_attach_allow_foo_override",
+		  "attach prog to %s unexpectedly succeeded\n", FOO))
+		goto err;
+
+	if (CHECK(bpf_prog_attach(drop_prog, foo, BPF_CGROUP_INET_EGRESS, 0),
+		  "prog_attach_drop_foo_none",
+		  "attach prog to %s failed, errno=%d\n", FOO, errno))
+		goto err;
+
+err:
+	close(foo);
+	close(bar);
+	close(allow_prog);
+	close(drop_prog);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_extern.c b/tools/testing/selftests/bpf/prog_tests/core_extern.c
new file mode 100644
index 000000000000..b093787e9448
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/core_extern.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <test_progs.h>
+#include <sys/mman.h>
+#include <sys/utsname.h>
+#include <linux/version.h>
+#include "test_core_extern.skel.h"
+
+static uint32_t get_kernel_version(void)
+{
+	uint32_t major, minor, patch;
+	struct utsname info;
+
+	uname(&info);
+	if (sscanf(info.release, "%u.%u.%u", &major, &minor, &patch) != 3)
+		return 0;
+	return KERNEL_VERSION(major, minor, patch);
+}
+
+#define CFG "CONFIG_BPF_SYSCALL=n\n"
+
+static struct test_case {
+	const char *name;
+	const char *cfg;
+	bool fails;
+	struct test_core_extern__data data;
+} test_cases[] = {
+	{ .name = "default search path", .data = { .bpf_syscall = true } },
+	{
+		.name = "custom values",
+		.cfg = "CONFIG_BPF_SYSCALL=n\n"
+		       "CONFIG_TRISTATE=m\n"
+		       "CONFIG_BOOL=y\n"
+		       "CONFIG_CHAR=100\n"
+		       "CONFIG_USHORT=30000\n"
+		       "CONFIG_INT=123456\n"
+		       "CONFIG_ULONG=0xDEADBEEFC0DE\n"
+		       "CONFIG_STR=\"abracad\"\n"
+		       "CONFIG_MISSING=0",
+		.data = {
+			.bpf_syscall = false,
+			.tristate_val = TRI_MODULE,
+			.bool_val = true,
+			.char_val = 100,
+			.ushort_val = 30000,
+			.int_val = 123456,
+			.ulong_val = 0xDEADBEEFC0DE,
+			.str_val = "abracad",
+		},
+	},
+	/* TRISTATE */
+	{ .name = "tristate (y)", .cfg = CFG"CONFIG_TRISTATE=y\n",
+	  .data = { .tristate_val = TRI_YES } },
+	{ .name = "tristate (n)", .cfg = CFG"CONFIG_TRISTATE=n\n",
+	  .data = { .tristate_val = TRI_NO } },
+	{ .name = "tristate (m)", .cfg = CFG"CONFIG_TRISTATE=m\n",
+	  .data = { .tristate_val = TRI_MODULE } },
+	{ .name = "tristate (int)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=1" },
+	{ .name = "tristate (bad)", .fails = 1, .cfg = CFG"CONFIG_TRISTATE=M" },
+	/* BOOL */
+	{ .name = "bool (y)", .cfg = CFG"CONFIG_BOOL=y\n",
+	  .data = { .bool_val = true } },
+	{ .name = "bool (n)", .cfg = CFG"CONFIG_BOOL=n\n",
+	  .data = { .bool_val = false } },
+	{ .name = "bool (tristate)", .fails = 1, .cfg = CFG"CONFIG_BOOL=m" },
+	{ .name = "bool (int)", .fails = 1, .cfg = CFG"CONFIG_BOOL=1" },
+	/* CHAR */
+	{ .name = "char (tristate)", .cfg = CFG"CONFIG_CHAR=m\n",
+	  .data = { .char_val = 'm' } },
+	{ .name = "char (bad)", .fails = 1, .cfg = CFG"CONFIG_CHAR=q\n" },
+	{ .name = "char (empty)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\n" },
+	{ .name = "char (str)", .fails = 1, .cfg = CFG"CONFIG_CHAR=\"y\"\n" },
+	/* STRING */
+	{ .name = "str (empty)", .cfg = CFG"CONFIG_STR=\"\"\n",
+	  .data = { .str_val = "\0\0\0\0\0\0\0" } },
+	{ .name = "str (padded)", .cfg = CFG"CONFIG_STR=\"abra\"\n",
+	  .data = { .str_val = "abra\0\0\0" } },
+	{ .name = "str (too long)", .cfg = CFG"CONFIG_STR=\"abracada\"\n",
+	  .data = { .str_val = "abracad" } },
+	{ .name = "str (no value)", .fails = 1, .cfg = CFG"CONFIG_STR=\n" },
+	{ .name = "str (bad value)", .fails = 1, .cfg = CFG"CONFIG_STR=bla\n" },
+	/* INTEGERS */
+	{
+		.name = "integer forms",
+		.cfg = CFG
+		       "CONFIG_CHAR=0xA\n"
+		       "CONFIG_USHORT=0462\n"
+		       "CONFIG_INT=-100\n"
+		       "CONFIG_ULONG=+1000000000000",
+		.data = {
+			.char_val = 0xA,
+			.ushort_val = 0462,
+			.int_val = -100,
+			.ulong_val = 1000000000000,
+		},
+	},
+	{ .name = "int (bad)", .fails = 1, .cfg = CFG"CONFIG_INT=abc" },
+	{ .name = "int (str)", .fails = 1, .cfg = CFG"CONFIG_INT=\"abc\"" },
+	{ .name = "int (empty)", .fails = 1, .cfg = CFG"CONFIG_INT=" },
+	{ .name = "int (mixed)", .fails = 1, .cfg = CFG"CONFIG_INT=123abc" },
+	{ .name = "int (max)", .cfg = CFG"CONFIG_INT=2147483647",
+	  .data = { .int_val = 2147483647 } },
+	{ .name = "int (min)", .cfg = CFG"CONFIG_INT=-2147483648",
+	  .data = { .int_val = -2147483648 } },
+	{ .name = "int (max+1)", .fails = 1, .cfg = CFG"CONFIG_INT=2147483648" },
+	{ .name = "int (min-1)", .fails = 1, .cfg = CFG"CONFIG_INT=-2147483649" },
+	{ .name = "ushort (max)", .cfg = CFG"CONFIG_USHORT=65535",
+	  .data = { .ushort_val = 65535 } },
+	{ .name = "ushort (min)", .cfg = CFG"CONFIG_USHORT=0",
+	  .data = { .ushort_val = 0 } },
+	{ .name = "ushort (max+1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=65536" },
+	{ .name = "ushort (min-1)", .fails = 1, .cfg = CFG"CONFIG_USHORT=-1" },
+	{ .name = "u64 (max)", .cfg = CFG"CONFIG_ULONG=0xffffffffffffffff",
+	  .data = { .ulong_val = 0xffffffffffffffff } },
+	{ .name = "u64 (min)", .cfg = CFG"CONFIG_ULONG=0",
+	  .data = { .ulong_val = 0 } },
+	{ .name = "u64 (max+1)", .fails = 1, .cfg = CFG"CONFIG_ULONG=0x10000000000000000" },
+};
+
+void test_core_extern(void)
+{
+	const uint32_t kern_ver = get_kernel_version();
+	int err, duration = 0, i, j;
+	struct test_core_extern *skel = NULL;
+	uint64_t *got, *exp;
+	int n = sizeof(*skel->data) / sizeof(uint64_t);
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		struct test_case *t = &test_cases[i];
+		DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
+			.kconfig = t->cfg,
+		);
+
+		if (!test__start_subtest(t->name))
+			continue;
+
+		skel = test_core_extern__open_opts(&opts);
+		if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
+			goto cleanup;
+		err = test_core_extern__load(skel);
+		if (t->fails) {
+			CHECK(!err, "skel_load",
+			      "shouldn't succeed open/load of skeleton\n");
+			goto cleanup;
+		} else if (CHECK(err, "skel_load",
+				 "failed to open/load skeleton\n")) {
+			goto cleanup;
+		}
+		err = test_core_extern__attach(skel);
+		if (CHECK(err, "attach_raw_tp", "failed attach: %d\n", err))
+			goto cleanup;
+
+		usleep(1);
+
+		t->data.kern_ver = kern_ver;
+		t->data.missing_val = 0xDEADC0DE;
+		got = (uint64_t *)skel->data;
+		exp = (uint64_t *)&t->data;
+		for (j = 0; j < n; j++) {
+			CHECK(got[j] != exp[j], "check_res",
+			      "result #%d: expected %lx, but got %lx\n",
+			       j, exp[j], got[j]);
+		}
+cleanup:
+		test_core_extern__destroy(skel);
+		skel = NULL;
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 05fe85281ff7..31e177adbdf1 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -74,6 +74,7 @@
 		.b123 = 2,						\
 		.c1c  = 3,						\
 		.d00d = 4,						\
+		.f10c = 0,						\
 	},								\
 	.output_len = sizeof(struct core_reloc_arrays_output)		\
 }
@@ -308,12 +309,15 @@ static struct core_reloc_test_case test_cases[] = {
 	ARRAYS_CASE(arrays),
 	ARRAYS_CASE(arrays___diff_arr_dim),
 	ARRAYS_CASE(arrays___diff_arr_val_sz),
+	ARRAYS_CASE(arrays___equiv_zero_sz_arr),
+	ARRAYS_CASE(arrays___fixed_arr),
 
 	ARRAYS_ERR_CASE(arrays___err_too_small),
 	ARRAYS_ERR_CASE(arrays___err_too_shallow),
 	ARRAYS_ERR_CASE(arrays___err_non_array),
 	ARRAYS_ERR_CASE(arrays___err_wrong_val_type1),
 	ARRAYS_ERR_CASE(arrays___err_wrong_val_type2),
+	ARRAYS_ERR_CASE(arrays___err_bad_zero_sz_arr),
 
 	/* enum/ptr/int handling scenarios */
 	PRIMITIVES_CASE(primitives),
diff --git a/tools/testing/selftests/bpf/prog_tests/cpu_mask.c b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
new file mode 100644
index 000000000000..f7c7e25232be
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cpu_mask.c
@@ -0,0 +1,78 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "bpf/libbpf_internal.h"
+
+static int duration = 0;
+
+static void validate_mask(int case_nr, const char *exp, bool *mask, int n)
+{
+	int i;
+
+	for (i = 0; exp[i]; i++) {
+		if (exp[i] == '1') {
+			if (CHECK(i + 1 > n, "mask_short",
+				  "case #%d: mask too short, got n=%d, need at least %d\n",
+				  case_nr, n, i + 1))
+				return;
+			CHECK(!mask[i], "cpu_not_set",
+			      "case #%d: mask differs, expected cpu#%d SET\n",
+			      case_nr, i);
+		} else {
+			CHECK(i < n && mask[i], "cpu_set",
+			      "case #%d: mask differs, expected cpu#%d UNSET\n",
+			      case_nr, i);
+		}
+	}
+	CHECK(i < n, "mask_long",
+	      "case #%d: mask too long, got n=%d, expected at most %d\n",
+	      case_nr, n, i);
+}
+
+static struct {
+	const char *cpu_mask;
+	const char *expect;
+	bool fails;
+} test_cases[] = {
+	{ "0\n", "1", false },
+	{ "0,2\n", "101", false },
+	{ "0-2\n", "111", false },
+	{ "0-2,3-4\n", "11111", false },
+	{ "0", "1", false },
+	{ "0-2", "111", false },
+	{ "0,2", "101", false },
+	{ "0,1-3", "1111", false },
+	{ "0,1,2,3", "1111", false },
+	{ "0,2-3,5", "101101", false },
+	{ "3-3", "0001", false },
+	{ "2-4,6,9-10", "00111010011", false },
+	/* failure cases */
+	{ "", "", true },
+	{ "0-", "", true },
+	{ "0 ", "", true },
+	{ "0_1", "", true },
+	{ "1-0", "", true },
+	{ "-1", "", true },
+};
+
+void test_cpu_mask()
+{
+	int i, err, n;
+	bool *mask;
+
+	for (i = 0; i < ARRAY_SIZE(test_cases); i++) {
+		mask = NULL;
+		err = parse_cpu_mask_str(test_cases[i].cpu_mask, &mask, &n);
+		if (test_cases[i].fails) {
+			CHECK(!err, "should_fail",
+			      "case #%d: parsing should fail!\n", i + 1);
+		} else {
+			if (CHECK(err, "parse_err",
+				  "case #%d: cpu mask parsing failed: %d\n",
+				  i + 1, err))
+				continue;
+			validate_mask(i + 1, test_cases[i].expect, mask, n);
+		}
+		free(mask);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 40bcff2cc274..235ac4f67f5b 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -1,90 +1,55 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
+#include "test_pkt_access.skel.h"
+#include "fentry_test.skel.h"
+#include "fexit_test.skel.h"
 
 void test_fentry_fexit(void)
 {
-	struct bpf_prog_load_attr attr_fentry = {
-		.file = "./fentry_test.o",
-	};
-	struct bpf_prog_load_attr attr_fexit = {
-		.file = "./fexit_test.o",
-	};
-
-	struct bpf_object *obj_fentry = NULL, *obj_fexit = NULL, *pkt_obj;
-	struct bpf_map *data_map_fentry, *data_map_fexit;
-	char fentry_name[] = "fentry/bpf_fentry_testX";
-	char fexit_name[] = "fexit/bpf_fentry_testX";
-	int err, pkt_fd, kfree_skb_fd, i;
-	struct bpf_link *link[12] = {};
-	struct bpf_program *prog[12];
-	__u32 duration, retval;
-	const int zero = 0;
-	u64 result[12];
-
-	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
-			    &pkt_obj, &pkt_fd);
-	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+	struct test_pkt_access *pkt_skel = NULL;
+	struct fentry_test *fentry_skel = NULL;
+	struct fexit_test *fexit_skel = NULL;
+	__u64 *fentry_res, *fexit_res;
+	__u32 duration = 0, retval;
+	int err, pkt_fd, i;
+
+	pkt_skel = test_pkt_access__open_and_load();
+	if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
 		return;
-	err = bpf_prog_load_xattr(&attr_fentry, &obj_fentry, &kfree_skb_fd);
-	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+	fentry_skel = fentry_test__open_and_load();
+	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
 		goto close_prog;
-	err = bpf_prog_load_xattr(&attr_fexit, &obj_fexit, &kfree_skb_fd);
-	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
+	fexit_skel = fexit_test__open_and_load();
+	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
 		goto close_prog;
 
-	for (i = 0; i < 6; i++) {
-		fentry_name[sizeof(fentry_name) - 2] = '1' + i;
-		prog[i] = bpf_object__find_program_by_title(obj_fentry, fentry_name);
-		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fentry_name))
-			goto close_prog;
-		link[i] = bpf_program__attach_trace(prog[i]);
-		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
-			goto close_prog;
-	}
-	data_map_fentry = bpf_object__find_map_by_name(obj_fentry, "fentry_t.bss");
-	if (CHECK(!data_map_fentry, "find_data_map", "data map not found\n"))
+	err = fentry_test__attach(fentry_skel);
+	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
 		goto close_prog;
-
-	for (i = 6; i < 12; i++) {
-		fexit_name[sizeof(fexit_name) - 2] = '1' + i - 6;
-		prog[i] = bpf_object__find_program_by_title(obj_fexit, fexit_name);
-		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", fexit_name))
-			goto close_prog;
-		link[i] = bpf_program__attach_trace(prog[i]);
-		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
-			goto close_prog;
-	}
-	data_map_fexit = bpf_object__find_map_by_name(obj_fexit, "fexit_te.bss");
-	if (CHECK(!data_map_fexit, "find_data_map", "data map not found\n"))
+	err = fexit_test__attach(fexit_skel);
+	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto close_prog;
 
+	pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
 	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				NULL, NULL, &retval, &duration);
 	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
-	err = bpf_map_lookup_elem(bpf_map__fd(data_map_fentry), &zero, &result);
-	if (CHECK(err, "get_result",
-		  "failed to get output data: %d\n", err))
-		goto close_prog;
-
-	err = bpf_map_lookup_elem(bpf_map__fd(data_map_fexit), &zero, result + 6);
-	if (CHECK(err, "get_result",
-		  "failed to get output data: %d\n", err))
-		goto close_prog;
-
-	for (i = 0; i < 12; i++)
-		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
-			  i % 6 + 1, result[i]))
-			goto close_prog;
+	fentry_res = (__u64 *)fentry_skel->bss;
+	fexit_res = (__u64 *)fexit_skel->bss;
+	printf("%lld\n", fentry_skel->bss->test1_result);
+	for (i = 0; i < 6; i++) {
+		CHECK(fentry_res[i] != 1, "result",
+		      "fentry_test%d failed err %lld\n", i + 1, fentry_res[i]);
+		CHECK(fexit_res[i] != 1, "result",
+		      "fexit_test%d failed err %lld\n", i + 1, fexit_res[i]);
+	}
 
 close_prog:
-	for (i = 0; i < 12; i++)
-		if (!IS_ERR_OR_NULL(link[i]))
-			bpf_link__destroy(link[i]);
-	bpf_object__close(obj_fentry);
-	bpf_object__close(obj_fexit);
-	bpf_object__close(pkt_obj);
+	test_pkt_access__destroy(pkt_skel);
+	fentry_test__destroy(fentry_skel);
+	fexit_test__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 9fb103193878..5cc06021f27d 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -1,64 +1,43 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2019 Facebook */
 #include <test_progs.h>
+#include "test_pkt_access.skel.h"
+#include "fentry_test.skel.h"
 
 void test_fentry_test(void)
 {
-	struct bpf_prog_load_attr attr = {
-		.file = "./fentry_test.o",
-	};
-
-	char prog_name[] = "fentry/bpf_fentry_testX";
-	struct bpf_object *obj = NULL, *pkt_obj;
-	int err, pkt_fd, kfree_skb_fd, i;
-	struct bpf_link *link[6] = {};
-	struct bpf_program *prog[6];
-	__u32 duration, retval;
-	struct bpf_map *data_map;
-	const int zero = 0;
-	u64 result[6];
-
-	err = bpf_prog_load("./test_pkt_access.o", BPF_PROG_TYPE_SCHED_CLS,
-			    &pkt_obj, &pkt_fd);
-	if (CHECK(err, "prog_load sched cls", "err %d errno %d\n", err, errno))
+	struct test_pkt_access *pkt_skel = NULL;
+	struct fentry_test *fentry_skel = NULL;
+	int err, pkt_fd, i;
+	__u32 duration = 0, retval;
+	__u64 *result;
+
+	pkt_skel = test_pkt_access__open_and_load();
+	if (CHECK(!pkt_skel, "pkt_skel_load", "pkt_access skeleton failed\n"))
 		return;
-	err = bpf_prog_load_xattr(&attr, &obj, &kfree_skb_fd);
-	if (CHECK(err, "prog_load fail", "err %d errno %d\n", err, errno))
-		goto close_prog;
+	fentry_skel = fentry_test__open_and_load();
+	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
+		goto cleanup;
 
-	for (i = 0; i < 6; i++) {
-		prog_name[sizeof(prog_name) - 2] = '1' + i;
-		prog[i] = bpf_object__find_program_by_title(obj, prog_name);
-		if (CHECK(!prog[i], "find_prog", "prog %s not found\n", prog_name))
-			goto close_prog;
-		link[i] = bpf_program__attach_trace(prog[i]);
-		if (CHECK(IS_ERR(link[i]), "attach_trace", "failed to link\n"))
-			goto close_prog;
-	}
-	data_map = bpf_object__find_map_by_name(obj, "fentry_t.bss");
-	if (CHECK(!data_map, "find_data_map", "data map not found\n"))
-		goto close_prog;
+	err = fentry_test__attach(fentry_skel);
+	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
+		goto cleanup;
 
+	pkt_fd = bpf_program__fd(pkt_skel->progs.test_pkt_access);
 	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v6, sizeof(pkt_v6),
 				NULL, NULL, &retval, &duration);
 	CHECK(err || retval, "ipv6",
 	      "err %d errno %d retval %d duration %d\n",
 	      err, errno, retval, duration);
 
-	err = bpf_map_lookup_elem(bpf_map__fd(data_map), &zero, &result);
-	if (CHECK(err, "get_result",
-		  "failed to get output data: %d\n", err))
-		goto close_prog;
-
-	for (i = 0; i < 6; i++)
-		if (CHECK(result[i] != 1, "result", "bpf_fentry_test%d failed err %ld\n",
-			  i + 1, result[i]))
-			goto close_prog;
+	result = (__u64 *)fentry_skel->bss;
+	for (i = 0; i < 6; i++) {
+		if (CHECK(result[i] != 1, "result",
+			  "fentry_test%d failed err %lld\n", i + 1, result[i]))
+			goto cleanup;
+	}
 
-close_prog:
-	for (i = 0; i < 6; i++)
-		if (!IS_ERR_OR_NULL(link[i]))
-			bpf_link__destroy(link[i]);
-	bpf_object__close(obj);
-	bpf_object__close(pkt_obj);
+cleanup:
+	fentry_test__destroy(fentry_skel);
+	test_pkt_access__destroy(pkt_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index b426bf2f97e4..cde463af7071 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -11,7 +11,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 	int err, pkt_fd, i;
 	struct bpf_link **link = NULL;
 	struct bpf_program **prog = NULL;
-	__u32 duration, retval;
+	__u32 duration = 0, retval;
 	struct bpf_map *data_map;
 	const int zero = 0;
 	u64 *result = NULL;
@@ -26,7 +26,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 
 	link = calloc(sizeof(struct bpf_link *), prog_cnt);
 	prog = calloc(sizeof(struct bpf_program *), prog_cnt);
-	result = malloc(prog_cnt * sizeof(u64));
+	result = malloc((prog_cnt + 32 /* spare */) * sizeof(u64));
 	if (CHECK(!link || !prog || !result, "alloc_memory",
 		  "failed to alloc memory"))
 		goto close_prog;
@@ -98,6 +98,24 @@ static void test_target_yes_callees(void)
 		"fexit/test_pkt_access",
 		"fexit/test_pkt_access_subprog1",
 		"fexit/test_pkt_access_subprog2",
+		"fexit/test_pkt_access_subprog3",
+	};
+	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
+				  "./test_pkt_access.o",
+				  ARRAY_SIZE(prog_name),
+				  prog_name);
+}
+
+static void test_func_replace(void)
+{
+	const char *prog_name[] = {
+		"fexit/test_pkt_access",
+		"fexit/test_pkt_access_subprog1",
+		"fexit/test_pkt_access_subprog2",
+		"fexit/test_pkt_access_subprog3",
+		"freplace/get_skb_len",
+		"freplace/get_skb_ifindex",
+		"freplace/get_constant",
 	};
 	test_fexit_bpf2bpf_common("./fexit_bpf2bpf.o",
 				  "./test_pkt_access.o",
@@ -109,4 +127,5 @@ void test_fexit_bpf2bpf(void)
 {
 	test_target_no_callees();
 	test_target_yes_callees();
+	test_func_replace();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index f99013222c74..d2c3655dd7a3 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -13,7 +13,7 @@ void test_fexit_test(void)
 	int err, pkt_fd, kfree_skb_fd, i;
 	struct bpf_link *link[6] = {};
 	struct bpf_program *prog[6];
-	__u32 duration, retval;
+	__u32 duration = 0, retval;
 	struct bpf_map *data_map;
 	const int zero = 0;
 	u64 result[6];
diff --git a/tools/testing/selftests/bpf/prog_tests/mmap.c b/tools/testing/selftests/bpf/prog_tests/mmap.c
index 051a6d48762c..16a814eb4d64 100644
--- a/tools/testing/selftests/bpf/prog_tests/mmap.c
+++ b/tools/testing/selftests/bpf/prog_tests/mmap.c
@@ -1,16 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 #include <sys/mman.h>
+#include "test_mmap.skel.h"
 
 struct map_data {
 	__u64 val[512 * 4];
 };
 
-struct bss_data {
-	__u64 in_val;
-	__u64 out_val;
-};
-
 static size_t roundup_page(size_t sz)
 {
 	long page_size = sysconf(_SC_PAGE_SIZE);
@@ -19,41 +15,25 @@ static size_t roundup_page(size_t sz)
 
 void test_mmap(void)
 {
-	const char *file = "test_mmap.o";
-	const char *probe_name = "raw_tracepoint/sys_enter";
-	const char *tp_name = "sys_enter";
-	const size_t bss_sz = roundup_page(sizeof(struct bss_data));
+	const size_t bss_sz = roundup_page(sizeof(struct test_mmap__bss));
 	const size_t map_sz = roundup_page(sizeof(struct map_data));
 	const int zero = 0, one = 1, two = 2, far = 1500;
 	const long page_size = sysconf(_SC_PAGE_SIZE);
 	int err, duration = 0, i, data_map_fd;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_link *link = NULL;
 	struct bpf_map *data_map, *bss_map;
 	void *bss_mmaped = NULL, *map_mmaped = NULL, *tmp1, *tmp2;
-	volatile struct bss_data *bss_data;
-	volatile struct map_data *map_data;
+	struct test_mmap__bss *bss_data;
+	struct map_data *map_data;
+	struct test_mmap *skel;
 	__u64 val = 0;
 
-	obj = bpf_object__open_file("test_mmap.o", NULL);
-	if (CHECK(IS_ERR(obj), "obj_open", "failed to open '%s': %ld\n",
-		  file, PTR_ERR(obj)))
+
+	skel = test_mmap__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
 		return;
-	prog = bpf_object__find_program_by_title(obj, probe_name);
-	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", probe_name))
-		goto cleanup;
-	err = bpf_object__load(obj);
-	if (CHECK(err, "obj_load", "failed to load prog '%s': %d\n",
-		  probe_name, err))
-		goto cleanup;
 
-	bss_map = bpf_object__find_map_by_name(obj, "test_mma.bss");
-	if (CHECK(!bss_map, "find_bss_map", ".bss map not found\n"))
-		goto cleanup;
-	data_map = bpf_object__find_map_by_name(obj, "data_map");
-	if (CHECK(!data_map, "find_data_map", "data_map map not found\n"))
-		goto cleanup;
+	bss_map = skel->maps.bss;
+	data_map = skel->maps.data_map;
 	data_map_fd = bpf_map__fd(data_map);
 
 	bss_mmaped = mmap(NULL, bss_sz, PROT_READ | PROT_WRITE, MAP_SHARED,
@@ -77,13 +57,15 @@ void test_mmap(void)
 
 	CHECK_FAIL(bss_data->in_val);
 	CHECK_FAIL(bss_data->out_val);
+	CHECK_FAIL(skel->bss->in_val);
+	CHECK_FAIL(skel->bss->out_val);
 	CHECK_FAIL(map_data->val[0]);
 	CHECK_FAIL(map_data->val[1]);
 	CHECK_FAIL(map_data->val[2]);
 	CHECK_FAIL(map_data->val[far]);
 
-	link = bpf_program__attach_raw_tracepoint(prog, tp_name);
-	if (CHECK(IS_ERR(link), "attach_raw_tp", "err %ld\n", PTR_ERR(link)))
+	err = test_mmap__attach(skel);
+	if (CHECK(err, "attach_raw_tp", "err %d\n", err))
 		goto cleanup;
 
 	bss_data->in_val = 123;
@@ -94,6 +76,8 @@ void test_mmap(void)
 
 	CHECK_FAIL(bss_data->in_val != 123);
 	CHECK_FAIL(bss_data->out_val != 123);
+	CHECK_FAIL(skel->bss->in_val != 123);
+	CHECK_FAIL(skel->bss->out_val != 123);
 	CHECK_FAIL(map_data->val[0] != 111);
 	CHECK_FAIL(map_data->val[1] != 222);
 	CHECK_FAIL(map_data->val[2] != 123);
@@ -160,6 +144,8 @@ void test_mmap(void)
 	usleep(1);
 	CHECK_FAIL(bss_data->in_val != 321);
 	CHECK_FAIL(bss_data->out_val != 321);
+	CHECK_FAIL(skel->bss->in_val != 321);
+	CHECK_FAIL(skel->bss->out_val != 321);
 	CHECK_FAIL(map_data->val[0] != 111);
 	CHECK_FAIL(map_data->val[1] != 222);
 	CHECK_FAIL(map_data->val[2] != 321);
@@ -203,6 +189,8 @@ void test_mmap(void)
 	map_data = tmp2;
 	CHECK_FAIL(bss_data->in_val != 321);
 	CHECK_FAIL(bss_data->out_val != 321);
+	CHECK_FAIL(skel->bss->in_val != 321);
+	CHECK_FAIL(skel->bss->out_val != 321);
 	CHECK_FAIL(map_data->val[0] != 111);
 	CHECK_FAIL(map_data->val[1] != 222);
 	CHECK_FAIL(map_data->val[2] != 321);
@@ -214,7 +202,5 @@ cleanup:
 		CHECK_FAIL(munmap(bss_mmaped, bss_sz));
 	if (map_mmaped)
 		CHECK_FAIL(munmap(map_mmaped, map_sz));
-	if (!IS_ERR_OR_NULL(link))
-		bpf_link__destroy(link);
-	bpf_object__close(obj);
+	test_mmap__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 3003fddc0613..1450ea2dd4cc 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -4,6 +4,7 @@
 #include <sched.h>
 #include <sys/socket.h>
 #include <test_progs.h>
+#include "bpf/libbpf_internal.h"
 
 static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 {
@@ -19,7 +20,7 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 
 void test_perf_buffer(void)
 {
-	int err, prog_fd, nr_cpus, i, duration = 0;
+	int err, prog_fd, on_len, nr_on_cpus = 0,  nr_cpus, i, duration = 0;
 	const char *prog_name = "kprobe/sys_nanosleep";
 	const char *file = "./test_perf_buffer.o";
 	struct perf_buffer_opts pb_opts = {};
@@ -29,15 +30,27 @@ void test_perf_buffer(void)
 	struct bpf_object *obj;
 	struct perf_buffer *pb;
 	struct bpf_link *link;
+	bool *online;
 
 	nr_cpus = libbpf_num_possible_cpus();
 	if (CHECK(nr_cpus < 0, "nr_cpus", "err %d\n", nr_cpus))
 		return;
 
+	err = parse_cpu_mask_file("/sys/devices/system/cpu/online",
+				  &online, &on_len);
+	if (CHECK(err, "nr_on_cpus", "err %d\n", err))
+		return;
+
+	for (i = 0; i < on_len; i++)
+		if (online[i])
+			nr_on_cpus++;
+
 	/* load program */
 	err = bpf_prog_load(file, BPF_PROG_TYPE_KPROBE, &obj, &prog_fd);
-	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
-		return;
+	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno)) {
+		obj = NULL;
+		goto out_close;
+	}
 
 	prog = bpf_object__find_program_by_title(obj, prog_name);
 	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", prog_name))
@@ -64,6 +77,11 @@ void test_perf_buffer(void)
 	/* trigger kprobe on every CPU */
 	CPU_ZERO(&cpu_seen);
 	for (i = 0; i < nr_cpus; i++) {
+		if (i >= on_len || !online[i]) {
+			printf("skipping offline CPU #%d\n", i);
+			continue;
+		}
+
 		CPU_ZERO(&cpu_set);
 		CPU_SET(i, &cpu_set);
 
@@ -81,8 +99,8 @@ void test_perf_buffer(void)
 	if (CHECK(err < 0, "perf_buffer__poll", "err %d\n", err))
 		goto out_free_pb;
 
-	if (CHECK(CPU_COUNT(&cpu_seen) != nr_cpus, "seen_cpu_cnt",
-		  "expect %d, seen %d\n", nr_cpus, CPU_COUNT(&cpu_seen)))
+	if (CHECK(CPU_COUNT(&cpu_seen) != nr_on_cpus, "seen_cpu_cnt",
+		  "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen)))
 		goto out_free_pb;
 
 out_free_pb:
@@ -91,4 +109,5 @@ out_detach:
 	bpf_link__destroy(link);
 out_close:
 	bpf_object__close(obj);
+	free(online);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
index 8a3187dec048..7aecfd9e87d1 100644
--- a/tools/testing/selftests/bpf/prog_tests/probe_user.c
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -3,8 +3,7 @@
 
 void test_probe_user(void)
 {
-#define kprobe_name "__sys_connect"
-	const char *prog_name = "kprobe/" kprobe_name;
+	const char *prog_name = "kprobe/__sys_connect";
 	const char *obj_file = "./test_probe_user.o";
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, );
 	int err, results_map_fd, sock_fd, duration = 0;
@@ -33,8 +32,7 @@ void test_probe_user(void)
 		  "err %d\n", results_map_fd))
 		goto cleanup;
 
-	kprobe_link = bpf_program__attach_kprobe(kprobe_prog, false,
-						 kprobe_name);
+	kprobe_link = bpf_program__attach(kprobe_prog);
 	if (CHECK(IS_ERR(kprobe_link), "attach_kprobe",
 		  "err %ld\n", PTR_ERR(kprobe_link))) {
 		kprobe_link = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
index d90acc13d1ec..563e12120e77 100644
--- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
+++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
@@ -16,14 +16,11 @@ struct rdonly_map_subtest {
 
 void test_rdonly_maps(void)
 {
-	const char *prog_name_skip_loop = "raw_tracepoint/sys_enter:skip_loop";
-	const char *prog_name_part_loop = "raw_tracepoint/sys_enter:part_loop";
-	const char *prog_name_full_loop = "raw_tracepoint/sys_enter:full_loop";
 	const char *file = "test_rdonly_maps.o";
 	struct rdonly_map_subtest subtests[] = {
-		{ "skip loop", prog_name_skip_loop, 0, 0 },
-		{ "part loop", prog_name_part_loop, 3, 2 + 3 + 4 },
-		{ "full loop", prog_name_full_loop, 4, 2 + 3 + 4 + 5 },
+		{ "skip loop", "skip_loop", 0, 0 },
+		{ "part loop", "part_loop", 3, 2 + 3 + 4 },
+		{ "full loop", "full_loop", 4, 2 + 3 + 4 + 5 },
 	};
 	int i, err, zero = 0, duration = 0;
 	struct bpf_link *link = NULL;
@@ -50,7 +47,7 @@ void test_rdonly_maps(void)
 		if (!test__start_subtest(t->subtest_name))
 			continue;
 
-		prog = bpf_object__find_program_by_title(obj, t->prog_name);
+		prog = bpf_object__find_program_by_name(obj, t->prog_name);
 		if (CHECK(!prog, "find_prog", "prog '%s' not found\n",
 			  t->prog_name))
 			goto cleanup;
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
new file mode 100644
index 000000000000..098bcae5f827
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -0,0 +1,838 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <sys/types.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+
+#include "test_progs.h"
+#include "test_select_reuseport_common.h"
+
+#define MAX_TEST_NAME 80
+#define MIN_TCPHDR_LEN 20
+#define UDPHDR_LEN 8
+
+#define TCP_SYNCOOKIE_SYSCTL "/proc/sys/net/ipv4/tcp_syncookies"
+#define TCP_FO_SYSCTL "/proc/sys/net/ipv4/tcp_fastopen"
+#define REUSEPORT_ARRAY_SIZE 32
+
+static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
+static __u32 expected_results[NR_RESULTS];
+static int sk_fds[REUSEPORT_ARRAY_SIZE];
+static int reuseport_array = -1, outer_map = -1;
+static int select_by_skb_data_prog;
+static int saved_tcp_syncookie = -1;
+static struct bpf_object *obj;
+static int saved_tcp_fo = -1;
+static __u32 index_zero;
+static int epfd;
+
+static union sa46 {
+	struct sockaddr_in6 v6;
+	struct sockaddr_in v4;
+	sa_family_t family;
+} srv_sa;
+
+#define RET_IF(condition, tag, format...) ({				\
+	if (CHECK_FAIL(condition)) {					\
+		printf(tag " " format);					\
+		return;							\
+	}								\
+})
+
+#define RET_ERR(condition, tag, format...) ({				\
+	if (CHECK_FAIL(condition)) {					\
+		printf(tag " " format);					\
+		return -1;						\
+	}								\
+})
+
+static int create_maps(void)
+{
+	struct bpf_create_map_attr attr = {};
+
+	/* Creating reuseport_array */
+	attr.name = "reuseport_array";
+	attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
+	attr.key_size = sizeof(__u32);
+	attr.value_size = sizeof(__u32);
+	attr.max_entries = REUSEPORT_ARRAY_SIZE;
+
+	reuseport_array = bpf_create_map_xattr(&attr);
+	RET_ERR(reuseport_array == -1, "creating reuseport_array",
+		"reuseport_array:%d errno:%d\n", reuseport_array, errno);
+
+	/* Creating outer_map */
+	attr.name = "outer_map";
+	attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS;
+	attr.key_size = sizeof(__u32);
+	attr.value_size = sizeof(__u32);
+	attr.max_entries = 1;
+	attr.inner_map_fd = reuseport_array;
+	outer_map = bpf_create_map_xattr(&attr);
+	RET_ERR(outer_map == -1, "creating outer_map",
+		"outer_map:%d errno:%d\n", outer_map, errno);
+
+	return 0;
+}
+
+static int prepare_bpf_obj(void)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	int err;
+
+	obj = bpf_object__open("test_select_reuseport_kern.o");
+	RET_ERR(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o",
+		"obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj));
+
+	map = bpf_object__find_map_by_name(obj, "outer_map");
+	RET_ERR(!map, "find outer_map", "!map\n");
+	err = bpf_map__reuse_fd(map, outer_map);
+	RET_ERR(err, "reuse outer_map", "err:%d\n", err);
+
+	err = bpf_object__load(obj);
+	RET_ERR(err, "load bpf_object", "err:%d\n", err);
+
+	prog = bpf_program__next(NULL, obj);
+	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 == -1, "get prog fd",
+		"select_by_skb_data_prog:%d\n", select_by_skb_data_prog);
+
+	map = bpf_object__find_map_by_name(obj, "result_map");
+	RET_ERR(!map, "find result_map", "!map\n");
+	result_map = bpf_map__fd(map);
+	RET_ERR(result_map == -1, "get result_map fd",
+		"result_map:%d\n", result_map);
+
+	map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map");
+	RET_ERR(!map, "find tmp_index_ovr_map\n", "!map");
+	tmp_index_ovr_map = bpf_map__fd(map);
+	RET_ERR(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd",
+		"tmp_index_ovr_map:%d\n", tmp_index_ovr_map);
+
+	map = bpf_object__find_map_by_name(obj, "linum_map");
+	RET_ERR(!map, "find linum_map", "!map\n");
+	linum_map = bpf_map__fd(map);
+	RET_ERR(linum_map == -1, "get linum_map fd",
+		"linum_map:%d\n", linum_map);
+
+	map = bpf_object__find_map_by_name(obj, "data_check_map");
+	RET_ERR(!map, "find data_check_map", "!map\n");
+	data_check_map = bpf_map__fd(map);
+	RET_ERR(data_check_map == -1, "get data_check_map fd",
+		"data_check_map:%d\n", data_check_map);
+
+	return 0;
+}
+
+static void sa46_init_loopback(union sa46 *sa, sa_family_t family)
+{
+	memset(sa, 0, sizeof(*sa));
+	sa->family = family;
+	if (sa->family == AF_INET6)
+		sa->v6.sin6_addr = in6addr_loopback;
+	else
+		sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+}
+
+static void sa46_init_inany(union sa46 *sa, sa_family_t family)
+{
+	memset(sa, 0, sizeof(*sa));
+	sa->family = family;
+	if (sa->family == AF_INET6)
+		sa->v6.sin6_addr = in6addr_any;
+	else
+		sa->v4.sin_addr.s_addr = INADDR_ANY;
+}
+
+static int read_int_sysctl(const char *sysctl)
+{
+	char buf[16];
+	int fd, ret;
+
+	fd = open(sysctl, 0);
+	RET_ERR(fd == -1, "open(sysctl)",
+		"sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno);
+
+	ret = read(fd, buf, sizeof(buf));
+	RET_ERR(ret <= 0, "read(sysctl)",
+		"sysctl:%s ret:%d errno:%d\n", sysctl, ret, errno);
+
+	close(fd);
+	return atoi(buf);
+}
+
+static int write_int_sysctl(const char *sysctl, int v)
+{
+	int fd, ret, size;
+	char buf[16];
+
+	fd = open(sysctl, O_RDWR);
+	RET_ERR(fd == -1, "open(sysctl)",
+		"sysctl:%s fd:%d errno:%d\n", sysctl, fd, errno);
+
+	size = snprintf(buf, sizeof(buf), "%d", v);
+	ret = write(fd, buf, size);
+	RET_ERR(ret != size, "write(sysctl)",
+		"sysctl:%s ret:%d size:%d errno:%d\n",
+		sysctl, ret, size, errno);
+
+	close(fd);
+	return 0;
+}
+
+static void restore_sysctls(void)
+{
+	if (saved_tcp_fo != -1)
+		write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
+	if (saved_tcp_syncookie != -1)
+		write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
+}
+
+static int enable_fastopen(void)
+{
+	int fo;
+
+	fo = read_int_sysctl(TCP_FO_SYSCTL);
+	if (fo < 0)
+		return -1;
+
+	return write_int_sysctl(TCP_FO_SYSCTL, fo | 7);
+}
+
+static int enable_syncookie(void)
+{
+	return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2);
+}
+
+static int disable_syncookie(void)
+{
+	return write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0);
+}
+
+static long get_linum(void)
+{
+	__u32 linum;
+	int err;
+
+	err = bpf_map_lookup_elem(linum_map, &index_zero, &linum);
+	RET_ERR(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n",
+		err, errno);
+
+	return linum;
+}
+
+static void check_data(int type, sa_family_t family, const struct cmd *cmd,
+		       int cli_fd)
+{
+	struct data_check expected = {}, result;
+	union sa46 cli_sa;
+	socklen_t addrlen;
+	int err;
+
+	addrlen = sizeof(cli_sa);
+	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa,
+			  &addrlen);
+	RET_IF(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n",
+	       err, errno);
+
+	err = bpf_map_lookup_elem(data_check_map, &index_zero, &result);
+	RET_IF(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
+	       err, errno);
+
+	if (type == SOCK_STREAM) {
+		expected.len = MIN_TCPHDR_LEN;
+		expected.ip_protocol = IPPROTO_TCP;
+	} else {
+		expected.len = UDPHDR_LEN;
+		expected.ip_protocol = IPPROTO_UDP;
+	}
+
+	if (family == AF_INET6) {
+		expected.eth_protocol = htons(ETH_P_IPV6);
+		expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[2] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[1] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[0];
+
+		memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32,
+		       sizeof(cli_sa.v6.sin6_addr));
+		memcpy(&expected.skb_addrs[4], &in6addr_loopback,
+		       sizeof(in6addr_loopback));
+		expected.skb_ports[0] = cli_sa.v6.sin6_port;
+		expected.skb_ports[1] = srv_sa.v6.sin6_port;
+	} else {
+		expected.eth_protocol = htons(ETH_P_IP);
+		expected.bind_inany = !srv_sa.v4.sin_addr.s_addr;
+
+		expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr;
+		expected.skb_addrs[1] = htonl(INADDR_LOOPBACK);
+		expected.skb_ports[0] = cli_sa.v4.sin_port;
+		expected.skb_ports[1] = srv_sa.v4.sin_port;
+	}
+
+	if (memcmp(&result, &expected, offsetof(struct data_check,
+						equal_check_end))) {
+		printf("unexpected data_check\n");
+		printf("  result: (0x%x, %u, %u)\n",
+		       result.eth_protocol, result.ip_protocol,
+		       result.bind_inany);
+		printf("expected: (0x%x, %u, %u)\n",
+		       expected.eth_protocol, expected.ip_protocol,
+		       expected.bind_inany);
+		RET_IF(1, "data_check result != expected",
+		       "bpf_prog_linum:%ld\n", get_linum());
+	}
+
+	RET_IF(!result.hash, "data_check result.hash empty",
+	       "result.hash:%u", result.hash);
+
+	expected.len += cmd ? sizeof(*cmd) : 0;
+	if (type == SOCK_STREAM)
+		RET_IF(expected.len > result.len, "expected.len > result.len",
+		       "expected.len:%u result.len:%u bpf_prog_linum:%ld\n",
+		       expected.len, result.len, get_linum());
+	else
+		RET_IF(expected.len != result.len, "expected.len != result.len",
+		       "expected.len:%u result.len:%u bpf_prog_linum:%ld\n",
+		       expected.len, result.len, get_linum());
+}
+
+static const char *result_to_str(enum result res)
+{
+	switch (res) {
+	case DROP_ERR_INNER_MAP:
+		return "DROP_ERR_INNER_MAP";
+	case DROP_ERR_SKB_DATA:
+		return "DROP_ERR_SKB_DATA";
+	case DROP_ERR_SK_SELECT_REUSEPORT:
+		return "DROP_ERR_SK_SELECT_REUSEPORT";
+	case DROP_MISC:
+		return "DROP_MISC";
+	case PASS:
+		return "PASS";
+	case PASS_ERR_SK_SELECT_REUSEPORT:
+		return "PASS_ERR_SK_SELECT_REUSEPORT";
+	default:
+		return "UNKNOWN";
+	}
+}
+
+static void check_results(void)
+{
+	__u32 results[NR_RESULTS];
+	__u32 i, broken = 0;
+	int err;
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &results[i]);
+		RET_IF(err == -1, "lookup_elem(result_map)",
+		       "i:%u err:%d errno:%d\n", i, err, errno);
+	}
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		if (results[i] != expected_results[i]) {
+			broken = i;
+			break;
+		}
+	}
+
+	if (i == NR_RESULTS)
+		return;
+
+	printf("unexpected result\n");
+	printf(" result: [");
+	printf("%u", results[0]);
+	for (i = 1; i < NR_RESULTS; i++)
+		printf(", %u", results[i]);
+	printf("]\n");
+
+	printf("expected: [");
+	printf("%u", expected_results[0]);
+	for (i = 1; i < NR_RESULTS; i++)
+		printf(", %u", expected_results[i]);
+	printf("]\n");
+
+	printf("mismatch on %s (bpf_prog_linum:%ld)\n", result_to_str(broken),
+	       get_linum());
+
+	CHECK_FAIL(true);
+}
+
+static int send_data(int type, sa_family_t family, void *data, size_t len,
+		     enum result expected)
+{
+	union sa46 cli_sa;
+	int fd, err;
+
+	fd = socket(family, type, 0);
+	RET_ERR(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno);
+
+	sa46_init_loopback(&cli_sa, family);
+	err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa));
+	RET_ERR(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno);
+
+	err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa,
+		     sizeof(srv_sa));
+	RET_ERR(err != len && expected >= PASS,
+		"sendto()", "family:%u err:%d errno:%d expected:%d\n",
+		family, err, errno, expected);
+
+	return fd;
+}
+
+static void do_test(int type, sa_family_t family, struct cmd *cmd,
+		    enum result expected)
+{
+	int nev, srv_fd, cli_fd;
+	struct epoll_event ev;
+	struct cmd rcv_cmd;
+	ssize_t nread;
+
+	cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0,
+			   expected);
+	if (cli_fd < 0)
+		return;
+	nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0);
+	RET_IF((nev <= 0 && expected >= PASS) ||
+	       (nev > 0 && expected < PASS),
+	       "nev <> expected",
+	       "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n",
+	       nev, expected, type, family,
+	       cmd ? cmd->reuseport_index : -1,
+	       cmd ? cmd->pass_on_failure : -1);
+	check_results();
+	check_data(type, family, cmd, cli_fd);
+
+	if (expected < PASS)
+		return;
+
+	RET_IF(expected != PASS_ERR_SK_SELECT_REUSEPORT &&
+	       cmd->reuseport_index != ev.data.u32,
+	       "check cmd->reuseport_index",
+	       "cmd:(%u, %u) ev.data.u32:%u\n",
+	       cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32);
+
+	srv_fd = sk_fds[ev.data.u32];
+	if (type == SOCK_STREAM) {
+		int new_fd = accept(srv_fd, NULL, 0);
+
+		RET_IF(new_fd == -1, "accept(srv_fd)",
+		       "ev.data.u32:%u new_fd:%d errno:%d\n",
+		       ev.data.u32, new_fd, errno);
+
+		nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+		RET_IF(nread != sizeof(rcv_cmd),
+		       "recv(new_fd)",
+		       "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+		       ev.data.u32, nread, sizeof(rcv_cmd), errno);
+
+		close(new_fd);
+	} else {
+		nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+		RET_IF(nread != sizeof(rcv_cmd),
+		       "recv(sk_fds)",
+		       "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+		       ev.data.u32, nread, sizeof(rcv_cmd), errno);
+	}
+
+	close(cli_fd);
+}
+
+static void test_err_inner_map(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = 0,
+		.pass_on_failure = 0,
+	};
+
+	expected_results[DROP_ERR_INNER_MAP]++;
+	do_test(type, family, &cmd, DROP_ERR_INNER_MAP);
+}
+
+static void test_err_skb_data(int type, sa_family_t family)
+{
+	expected_results[DROP_ERR_SKB_DATA]++;
+	do_test(type, family, NULL, DROP_ERR_SKB_DATA);
+}
+
+static void test_err_sk_select_port(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = REUSEPORT_ARRAY_SIZE,
+		.pass_on_failure = 0,
+	};
+
+	expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++;
+	do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT);
+}
+
+static void test_pass(int type, sa_family_t family)
+{
+	struct cmd cmd;
+	int i;
+
+	cmd.pass_on_failure = 0;
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+		expected_results[PASS]++;
+		cmd.reuseport_index = i;
+		do_test(type, family, &cmd, PASS);
+	}
+}
+
+static void test_syncookie(int type, sa_family_t family)
+{
+	int err, tmp_index = 1;
+	struct cmd cmd = {
+		.reuseport_index = 0,
+		.pass_on_failure = 0,
+	};
+
+	if (type != SOCK_STREAM)
+		return;
+
+	/*
+	 * +1 for TCP-SYN and
+	 * +1 for the TCP-ACK (ack the syncookie)
+	 */
+	expected_results[PASS] += 2;
+	enable_syncookie();
+	/*
+	 * Simulate TCP-SYN and TCP-ACK are handled by two different sk:
+	 * TCP-SYN: select sk_fds[tmp_index = 1] tmp_index is from the
+	 *          tmp_index_ovr_map
+	 * TCP-ACK: select sk_fds[reuseport_index = 0] reuseport_index
+	 *          is from the cmd.reuseport_index
+	 */
+	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero,
+				  &tmp_index, BPF_ANY);
+	RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)",
+	       "err:%d errno:%d\n", err, errno);
+	do_test(type, family, &cmd, PASS);
+	err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero,
+				  &tmp_index);
+	RET_IF(err == -1 || tmp_index != -1,
+	       "lookup_elem(tmp_index_ovr_map)",
+	       "err:%d errno:%d tmp_index:%d\n",
+	       err, errno, tmp_index);
+	disable_syncookie();
+}
+
+static void test_pass_on_err(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = REUSEPORT_ARRAY_SIZE,
+		.pass_on_failure = 1,
+	};
+
+	expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1;
+	do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT);
+}
+
+static void test_detach_bpf(int type, sa_family_t family)
+{
+#ifdef SO_DETACH_REUSEPORT_BPF
+	__u32 nr_run_before = 0, nr_run_after = 0, tmp, i;
+	struct epoll_event ev;
+	int cli_fd, err, nev;
+	struct cmd cmd = {};
+	int optvalue = 0;
+
+	err = setsockopt(sk_fds[0], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF,
+			 &optvalue, sizeof(optvalue));
+	RET_IF(err == -1, "setsockopt(SO_DETACH_REUSEPORT_BPF)",
+	       "err:%d errno:%d\n", err, errno);
+
+	err = setsockopt(sk_fds[1], SOL_SOCKET, SO_DETACH_REUSEPORT_BPF,
+			 &optvalue, sizeof(optvalue));
+	RET_IF(err == 0 || errno != ENOENT,
+	       "setsockopt(SO_DETACH_REUSEPORT_BPF)",
+	       "err:%d errno:%d\n", err, errno);
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &tmp);
+		RET_IF(err == -1, "lookup_elem(result_map)",
+		       "i:%u err:%d errno:%d\n", i, err, errno);
+		nr_run_before += tmp;
+	}
+
+	cli_fd = send_data(type, family, &cmd, sizeof(cmd), PASS);
+	if (cli_fd < 0)
+		return;
+	nev = epoll_wait(epfd, &ev, 1, 5);
+	RET_IF(nev <= 0, "nev <= 0",
+	       "nev:%d expected:1 type:%d family:%d data:(0, 0)\n",
+	       nev,  type, family);
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &tmp);
+		RET_IF(err == -1, "lookup_elem(result_map)",
+		       "i:%u err:%d errno:%d\n", i, err, errno);
+		nr_run_after += tmp;
+	}
+
+	RET_IF(nr_run_before != nr_run_after,
+	       "nr_run_before != nr_run_after",
+	       "nr_run_before:%u nr_run_after:%u\n",
+	       nr_run_before, nr_run_after);
+
+	close(cli_fd);
+#else
+	test__skip();
+#endif
+}
+
+static void prepare_sk_fds(int type, sa_family_t family, bool inany)
+{
+	const int first = REUSEPORT_ARRAY_SIZE - 1;
+	int i, err, optval = 1;
+	struct epoll_event ev;
+	socklen_t addrlen;
+
+	if (inany)
+		sa46_init_inany(&srv_sa, family);
+	else
+		sa46_init_loopback(&srv_sa, family);
+	addrlen = sizeof(srv_sa);
+
+	/*
+	 * The sk_fds[] is filled from the back such that the order
+	 * is exactly opposite to the (struct sock_reuseport *)reuse->socks[].
+	 */
+	for (i = first; i >= 0; i--) {
+		sk_fds[i] = socket(family, type, 0);
+		RET_IF(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n",
+		       i, sk_fds[i], errno);
+		err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT,
+				 &optval, sizeof(optval));
+		RET_IF(err == -1, "setsockopt(SO_REUSEPORT)",
+		       "sk_fds[%d] err:%d errno:%d\n",
+		       i, err, errno);
+
+		if (i == first) {
+			err = setsockopt(sk_fds[i], SOL_SOCKET,
+					 SO_ATTACH_REUSEPORT_EBPF,
+					 &select_by_skb_data_prog,
+					 sizeof(select_by_skb_data_prog));
+			RET_IF(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
+			       "err:%d errno:%d\n", err, errno);
+		}
+
+		err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen);
+		RET_IF(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n",
+		       i, err, errno);
+
+		if (type == SOCK_STREAM) {
+			err = listen(sk_fds[i], 10);
+			RET_IF(err == -1, "listen()",
+			       "sk_fds[%d] err:%d errno:%d\n",
+			       i, err, errno);
+		}
+
+		err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i],
+					  BPF_NOEXIST);
+		RET_IF(err == -1, "update_elem(reuseport_array)",
+		       "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+
+		if (i == first) {
+			socklen_t addrlen = sizeof(srv_sa);
+
+			err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa,
+					  &addrlen);
+			RET_IF(err == -1, "getsockname()",
+			       "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+		}
+	}
+
+	epfd = epoll_create(1);
+	RET_IF(epfd == -1, "epoll_create(1)",
+	       "epfd:%d errno:%d\n", epfd, errno);
+
+	ev.events = EPOLLIN;
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+		ev.data.u32 = i;
+		err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev);
+		RET_IF(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i);
+	}
+}
+
+static void setup_per_test(int type, sa_family_t family, bool inany,
+			   bool no_inner_map)
+{
+	int ovr = -1, err;
+
+	prepare_sk_fds(type, family, inany);
+	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr,
+				  BPF_ANY);
+	RET_IF(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)",
+	       "err:%d errno:%d\n", err, errno);
+
+	/* Install reuseport_array to outer_map? */
+	if (no_inner_map)
+		return;
+
+	err = bpf_map_update_elem(outer_map, &index_zero, &reuseport_array,
+				  BPF_ANY);
+	RET_IF(err == -1, "update_elem(outer_map, 0, reuseport_array)",
+	       "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup_per_test(bool no_inner_map)
+{
+	int i, err, zero = 0;
+
+	memset(expected_results, 0, sizeof(expected_results));
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_update_elem(result_map, &i, &zero, BPF_ANY);
+		RET_IF(err, "reset elem in result_map",
+		       "i:%u err:%d errno:%d\n", i, err, errno);
+	}
+
+	err = bpf_map_update_elem(linum_map, &zero, &zero, BPF_ANY);
+	RET_IF(err, "reset line number in linum_map", "err:%d errno:%d\n",
+	       err, errno);
+
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++)
+		close(sk_fds[i]);
+	close(epfd);
+
+	/* Delete reuseport_array from outer_map? */
+	if (no_inner_map)
+		return;
+
+	err = bpf_map_delete_elem(outer_map, &index_zero);
+	RET_IF(err == -1, "delete_elem(outer_map)",
+	       "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup(void)
+{
+	if (outer_map != -1)
+		close(outer_map);
+	if (reuseport_array != -1)
+		close(reuseport_array);
+	if (obj)
+		bpf_object__close(obj);
+}
+
+static const char *family_str(sa_family_t family)
+{
+	switch (family) {
+	case AF_INET:
+		return "IPv4";
+	case AF_INET6:
+		return "IPv6";
+	default:
+		return "unknown";
+	}
+}
+
+static const char *sotype_str(int sotype)
+{
+	switch (sotype) {
+	case SOCK_STREAM:
+		return "TCP";
+	case SOCK_DGRAM:
+		return "UDP";
+	default:
+		return "unknown";
+	}
+}
+
+#define TEST_INIT(fn, ...) { fn, #fn, __VA_ARGS__ }
+
+static void test_config(int sotype, sa_family_t family, bool inany)
+{
+	const struct test {
+		void (*fn)(int sotype, sa_family_t family);
+		const char *name;
+		bool no_inner_map;
+	} tests[] = {
+		TEST_INIT(test_err_inner_map, true /* no_inner_map */),
+		TEST_INIT(test_err_skb_data),
+		TEST_INIT(test_err_sk_select_port),
+		TEST_INIT(test_pass),
+		TEST_INIT(test_syncookie),
+		TEST_INIT(test_pass_on_err),
+		TEST_INIT(test_detach_bpf),
+	};
+	char s[MAX_TEST_NAME];
+	const struct test *t;
+
+	for (t = tests; t < tests + ARRAY_SIZE(tests); t++) {
+		snprintf(s, sizeof(s), "%s/%s %s %s",
+			 family_str(family), sotype_str(sotype),
+			 inany ? "INANY" : "LOOPBACK", t->name);
+
+		if (!test__start_subtest(s))
+			continue;
+
+		setup_per_test(sotype, family, inany, t->no_inner_map);
+		t->fn(sotype, family);
+		cleanup_per_test(t->no_inner_map);
+	}
+}
+
+#define BIND_INANY true
+
+static void test_all(void)
+{
+	const struct config {
+		int sotype;
+		sa_family_t family;
+		bool inany;
+	} configs[] = {
+		{ SOCK_STREAM, AF_INET },
+		{ SOCK_STREAM, AF_INET, BIND_INANY },
+		{ SOCK_STREAM, AF_INET6 },
+		{ SOCK_STREAM, AF_INET6, BIND_INANY },
+		{ SOCK_DGRAM, AF_INET },
+		{ SOCK_DGRAM, AF_INET6 },
+	};
+	const struct config *c;
+
+	for (c = configs; c < configs + ARRAY_SIZE(configs); c++)
+		test_config(c->sotype, c->family, c->inany);
+}
+
+void test_select_reuseport(void)
+{
+	if (create_maps())
+		goto out;
+	if (prepare_bpf_obj())
+		goto out;
+
+	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
+	if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0)
+		goto out;
+
+	if (enable_fastopen())
+		goto out;
+	if (disable_syncookie())
+		goto out;
+
+	test_all();
+out:
+	cleanup();
+	restore_sysctls();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
index b607112c64e7..504abb7bfb95 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_send_signal_kern.skel.h"
 
 static volatile int sigusr1_received = 0;
 
@@ -9,17 +10,15 @@ static void sigusr1_handler(int signum)
 }
 
 static void test_send_signal_common(struct perf_event_attr *attr,
-				    int prog_type,
+				    bool signal_thread,
 				    const char *test_name)
 {
-	int err = -1, pmu_fd, prog_fd, info_map_fd, status_map_fd;
-	const char *file = "./test_send_signal_kern.o";
-	struct bpf_object *obj = NULL;
+	struct test_send_signal_kern *skel;
 	int pipe_c2p[2], pipe_p2c[2];
-	__u32 key = 0, duration = 0;
+	int err = -1, pmu_fd = -1;
+	__u32 duration = 0;
 	char buf[256];
 	pid_t pid;
-	__u64 val;
 
 	if (CHECK(pipe(pipe_c2p), test_name,
 		  "pipe pipe_c2p error: %s\n", strerror(errno)))
@@ -73,45 +72,39 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 	close(pipe_c2p[1]); /* close write */
 	close(pipe_p2c[0]); /* close read */
 
-	err = bpf_prog_load(file, prog_type, &obj, &prog_fd);
-	if (CHECK(err < 0, test_name, "bpf_prog_load error: %s\n",
-		  strerror(errno)))
-		goto prog_load_failure;
-
-	pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
-			 -1 /* group id */, 0 /* flags */);
-	if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
-		  strerror(errno))) {
-		err = -1;
-		goto close_prog;
-	}
+	skel = test_send_signal_kern__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open_and_load failed\n"))
+		goto skel_open_load_failure;
 
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0);
-	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_enable error: %s\n",
-		  strerror(errno)))
-		goto disable_pmu;
-
-	err = ioctl(pmu_fd, PERF_EVENT_IOC_SET_BPF, prog_fd);
-	if (CHECK(err < 0, test_name, "ioctl perf_event_ioc_set_bpf error: %s\n",
-		  strerror(errno)))
-		goto disable_pmu;
-
-	err = -1;
-	info_map_fd = bpf_object__find_map_fd_by_name(obj, "info_map");
-	if (CHECK(info_map_fd < 0, test_name, "find map %s error\n", "info_map"))
-		goto disable_pmu;
+	if (!attr) {
+		err = test_send_signal_kern__attach(skel);
+		if (CHECK(err, "skel_attach", "skeleton attach failed\n")) {
+			err = -1;
+			goto destroy_skel;
+		}
+	} else {
+		pmu_fd = syscall(__NR_perf_event_open, attr, pid, -1,
+				 -1 /* group id */, 0 /* flags */);
+		if (CHECK(pmu_fd < 0, test_name, "perf_event_open error: %s\n",
+			strerror(errno))) {
+			err = -1;
+			goto destroy_skel;
+		}
 
-	status_map_fd = bpf_object__find_map_fd_by_name(obj, "status_map");
-	if (CHECK(status_map_fd < 0, test_name, "find map %s error\n", "status_map"))
-		goto disable_pmu;
+		skel->links.send_signal_perf =
+			bpf_program__attach_perf_event(skel->progs.send_signal_perf, pmu_fd);
+		if (CHECK(IS_ERR(skel->links.send_signal_perf), "attach_perf_event",
+			  "err %ld\n", PTR_ERR(skel->links.send_signal_perf)))
+			goto disable_pmu;
+	}
 
 	/* wait until child signal handler installed */
 	read(pipe_c2p[0], buf, 1);
 
 	/* trigger the bpf send_signal */
-	key = 0;
-	val = (((__u64)(SIGUSR1)) << 32) | pid;
-	bpf_map_update_elem(info_map_fd, &key, &val, 0);
+	skel->bss->pid = pid;
+	skel->bss->sig = SIGUSR1;
+	skel->bss->signal_thread = signal_thread;
 
 	/* notify child that bpf program can send_signal now */
 	write(pipe_p2c[1], buf, 1);
@@ -132,46 +125,20 @@ static void test_send_signal_common(struct perf_event_attr *attr,
 
 disable_pmu:
 	close(pmu_fd);
-close_prog:
-	bpf_object__close(obj);
-prog_load_failure:
+destroy_skel:
+	test_send_signal_kern__destroy(skel);
+skel_open_load_failure:
 	close(pipe_c2p[0]);
 	close(pipe_p2c[1]);
 	wait(NULL);
 }
 
-static void test_send_signal_tracepoint(void)
+static void test_send_signal_tracepoint(bool signal_thread)
 {
-	const char *id_path = "/sys/kernel/debug/tracing/events/syscalls/sys_enter_nanosleep/id";
-	struct perf_event_attr attr = {
-		.type = PERF_TYPE_TRACEPOINT,
-		.sample_type = PERF_SAMPLE_RAW | PERF_SAMPLE_CALLCHAIN,
-		.sample_period = 1,
-		.wakeup_events = 1,
-	};
-	__u32 duration = 0;
-	int bytes, efd;
-	char buf[256];
-
-	efd = open(id_path, O_RDONLY, 0);
-	if (CHECK(efd < 0, "tracepoint",
-		  "open syscalls/sys_enter_nanosleep/id failure: %s\n",
-		  strerror(errno)))
-		return;
-
-	bytes = read(efd, buf, sizeof(buf));
-	close(efd);
-	if (CHECK(bytes <= 0 || bytes >= sizeof(buf), "tracepoint",
-		  "read syscalls/sys_enter_nanosleep/id failure: %s\n",
-		  strerror(errno)))
-		return;
-
-	attr.config = strtol(buf, NULL, 0);
-
-	test_send_signal_common(&attr, BPF_PROG_TYPE_TRACEPOINT, "tracepoint");
+	test_send_signal_common(NULL, signal_thread, "tracepoint");
 }
 
-static void test_send_signal_perf(void)
+static void test_send_signal_perf(bool signal_thread)
 {
 	struct perf_event_attr attr = {
 		.sample_period = 1,
@@ -179,15 +146,13 @@ static void test_send_signal_perf(void)
 		.config = PERF_COUNT_SW_CPU_CLOCK,
 	};
 
-	test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
-				"perf_sw_event");
+	test_send_signal_common(&attr, signal_thread, "perf_sw_event");
 }
 
-static void test_send_signal_nmi(void)
+static void test_send_signal_nmi(bool signal_thread)
 {
 	struct perf_event_attr attr = {
-		.sample_freq = 50,
-		.freq = 1,
+		.sample_period = 1,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
@@ -210,16 +175,21 @@ static void test_send_signal_nmi(void)
 		close(pmu_fd);
 	}
 
-	test_send_signal_common(&attr, BPF_PROG_TYPE_PERF_EVENT,
-				"perf_hw_event");
+	test_send_signal_common(&attr, signal_thread, "perf_hw_event");
 }
 
 void test_send_signal(void)
 {
 	if (test__start_subtest("send_signal_tracepoint"))
-		test_send_signal_tracepoint();
+		test_send_signal_tracepoint(false);
 	if (test__start_subtest("send_signal_perf"))
-		test_send_signal_perf();
+		test_send_signal_perf(false);
 	if (test__start_subtest("send_signal_nmi"))
-		test_send_signal_nmi();
+		test_send_signal_nmi(false);
+	if (test__start_subtest("send_signal_tracepoint_thread"))
+		test_send_signal_tracepoint(true);
+	if (test__start_subtest("send_signal_perf_thread"))
+		test_send_signal_perf(true);
+	if (test__start_subtest("send_signal_nmi_thread"))
+		test_send_signal_nmi(true);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index a2eb8db8dafb..c6d6b685a946 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -11,6 +11,9 @@ void test_skb_ctx(void)
 		.cb[4] = 5,
 		.priority = 6,
 		.tstamp = 7,
+		.wire_len = 100,
+		.gso_segs = 8,
+		.mark = 9,
 	};
 	struct bpf_prog_test_run_attr tattr = {
 		.data_in = &pkt_v4,
@@ -91,4 +94,8 @@ void test_skb_ctx(void)
 		   "ctx_out_tstamp",
 		   "skb->tstamp == %lld, expected %d\n",
 		   skb.tstamp, 8);
+	CHECK_ATTR(skb.mark != 10,
+		   "ctx_out_mark",
+		   "skb->mark == %u, expected %d\n",
+		   skb.mark, 10);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
new file mode 100644
index 000000000000..9264a2736018
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook */
+
+#include <test_progs.h>
+
+struct s {
+	int a;
+	long long b;
+} __attribute__((packed));
+
+#include "test_skeleton.skel.h"
+
+void test_skeleton(void)
+{
+	int duration = 0, err;
+	struct test_skeleton* skel;
+	struct test_skeleton__bss *bss;
+	struct test_skeleton__kconfig *kcfg;
+
+	skel = test_skeleton__open();
+	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+		return;
+
+	if (CHECK(skel->kconfig, "skel_kconfig", "kconfig is mmaped()!\n"))
+		goto cleanup;
+
+	err = test_skeleton__load(skel);
+	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
+		goto cleanup;
+
+	bss = skel->bss;
+	bss->in1 = 1;
+	bss->in2 = 2;
+	bss->in3 = 3;
+	bss->in4 = 4;
+	bss->in5.a = 5;
+	bss->in5.b = 6;
+	kcfg = skel->kconfig;
+
+	err = test_skeleton__attach(skel);
+	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	CHECK(bss->out1 != 1, "res1", "got %d != exp %d\n", bss->out1, 1);
+	CHECK(bss->out2 != 2, "res2", "got %lld != exp %d\n", bss->out2, 2);
+	CHECK(bss->out3 != 3, "res3", "got %d != exp %d\n", (int)bss->out3, 3);
+	CHECK(bss->out4 != 4, "res4", "got %lld != exp %d\n", bss->out4, 4);
+	CHECK(bss->handler_out5.a != 5, "res5", "got %d != exp %d\n",
+	      bss->handler_out5.a, 5);
+	CHECK(bss->handler_out5.b != 6, "res6", "got %lld != exp %d\n",
+	      bss->handler_out5.b, 6);
+
+	CHECK(bss->bpf_syscall != kcfg->CONFIG_BPF_SYSCALL, "ext1",
+	      "got %d != exp %d\n", bss->bpf_syscall, kcfg->CONFIG_BPF_SYSCALL);
+	CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2",
+	      "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION);
+
+cleanup:
+	test_skeleton__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
index d841dced971f..e8399ae50e77 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id.c
@@ -1,16 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_stacktrace_build_id.skel.h"
 
 void test_stacktrace_build_id(void)
 {
+
 	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
-	const char *prog_name = "tracepoint/random/urandom_read";
-	const char *file = "./test_stacktrace_build_id.o";
-	int err, prog_fd, stack_trace_len;
+	struct test_stacktrace_build_id *skel;
+	int err, stack_trace_len;
 	__u32 key, previous_key, val, duration = 0;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_link *link = NULL;
 	char buf[256];
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@@ -18,43 +16,24 @@ void test_stacktrace_build_id(void)
 	int retry = 1;
 
 retry:
-	err = bpf_prog_load(file, BPF_PROG_TYPE_TRACEPOINT, &obj, &prog_fd);
-	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+	skel = test_stacktrace_build_id__open_and_load();
+	if (CHECK(!skel, "skel_open_and_load", "skeleton open/load failed\n"))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
-		goto close_prog;
-
-	link = bpf_program__attach_tracepoint(prog, "random", "urandom_read");
-	if (CHECK(IS_ERR(link), "attach_tp", "err %ld\n", PTR_ERR(link)))
-		goto close_prog;
+	err = test_stacktrace_build_id__attach(skel);
+	if (CHECK(err, "attach_tp", "err %d\n", err))
+		goto cleanup;
 
 	/* find map fds */
-	control_map_fd = bpf_find_map(__func__, obj, "control_map");
-	if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
-
-	stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
-	if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
-
-	stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
-	if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
-		  err, errno))
-		goto disable_pmu;
-
-	stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
-	if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+	control_map_fd = bpf_map__fd(skel->maps.control_map);
+	stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap);
+	stackmap_fd = bpf_map__fd(skel->maps.stackmap);
+	stack_amap_fd = bpf_map__fd(skel->maps.stack_amap);
 
 	if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")))
-		goto disable_pmu;
+		goto cleanup;
 	if (CHECK_FAIL(system("./urandom_read")))
-		goto disable_pmu;
+		goto cleanup;
 	/* disable stack trace collection */
 	key = 0;
 	val = 1;
@@ -66,23 +45,23 @@ retry:
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
 	if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = extract_build_id(buf, 256);
 
 	if (CHECK(err, "get build_id with readelf",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = bpf_map_get_next_key(stackmap_fd, NULL, &key);
 	if (CHECK(err, "get_next_key from stackmap",
 		  "err %d, errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	do {
 		char build_id[64];
@@ -90,7 +69,7 @@ retry:
 		err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
 		if (CHECK(err, "lookup_elem from stackmap",
 			  "err %d, errno %d\n", err, errno))
-			goto disable_pmu;
+			goto cleanup;
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
 			if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
 			    id_offs[i].offset != 0) {
@@ -108,8 +87,7 @@ retry:
 	 * try it one more time.
 	 */
 	if (build_id_matches < 1 && retry--) {
-		bpf_link__destroy(link);
-		bpf_object__close(obj);
+		test_stacktrace_build_id__destroy(skel);
 		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
 		       __func__);
 		goto retry;
@@ -117,17 +95,14 @@ retry:
 
 	if (CHECK(build_id_matches < 1, "build id match",
 		  "Didn't find expected build ID from the map\n"))
-		goto disable_pmu;
+		goto cleanup;
 
-	stack_trace_len = PERF_MAX_STACK_DEPTH
-		* sizeof(struct bpf_stack_build_id);
+	stack_trace_len = PERF_MAX_STACK_DEPTH *
+			  sizeof(struct bpf_stack_build_id);
 	err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len);
 	CHECK(err, "compare_stack_ips stackmap vs. stack_amap",
 	      "err %d errno %d\n", err, errno);
 
-disable_pmu:
-	bpf_link__destroy(link);
-
-close_prog:
-	bpf_object__close(obj);
+cleanup:
+	test_stacktrace_build_id__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
index f62aa0eb959b..f002e3090d92 100644
--- a/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
+++ b/tools/testing/selftests/bpf/prog_tests/stacktrace_build_id_nmi.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
+#include "test_stacktrace_build_id.skel.h"
 
 static __u64 read_perf_max_sample_freq(void)
 {
@@ -16,19 +17,15 @@ static __u64 read_perf_max_sample_freq(void)
 
 void test_stacktrace_build_id_nmi(void)
 {
-	int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd;
-	const char *prog_name = "tracepoint/random/urandom_read";
-	const char *file = "./test_stacktrace_build_id.o";
-	int err, pmu_fd, prog_fd;
+	int control_map_fd, stackid_hmap_fd, stackmap_fd;
+	struct test_stacktrace_build_id *skel;
+	int err, pmu_fd;
 	struct perf_event_attr attr = {
 		.freq = 1,
 		.type = PERF_TYPE_HARDWARE,
 		.config = PERF_COUNT_HW_CPU_CYCLES,
 	};
 	__u32 key, previous_key, val, duration = 0;
-	struct bpf_program *prog;
-	struct bpf_object *obj;
-	struct bpf_link *link;
 	char buf[256];
 	int i, j;
 	struct bpf_stack_build_id id_offs[PERF_MAX_STACK_DEPTH];
@@ -38,54 +35,46 @@ void test_stacktrace_build_id_nmi(void)
 	attr.sample_freq = read_perf_max_sample_freq();
 
 retry:
-	err = bpf_prog_load(file, BPF_PROG_TYPE_PERF_EVENT, &obj, &prog_fd);
-	if (CHECK(err, "prog_load", "err %d errno %d\n", err, errno))
+	skel = test_stacktrace_build_id__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, prog_name);
-	if (CHECK(!prog, "find_prog", "prog '%s' not found\n", prog_name))
-		goto close_prog;
+	/* override program type */
+	bpf_program__set_perf_event(skel->progs.oncpu);
+
+	err = test_stacktrace_build_id__load(skel);
+	if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err))
+		goto cleanup;
 
 	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
 			 0 /* cpu 0 */, -1 /* group id */,
 			 0 /* flags */);
-	if (CHECK(pmu_fd < 0, "perf_event_open",
-		  "err %d errno %d. Does the test host support PERF_COUNT_HW_CPU_CYCLES?\n",
+	if (pmu_fd < 0 && errno == ENOENT) {
+		printf("%s:SKIP:no PERF_COUNT_HW_CPU_CYCLES\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
 		  pmu_fd, errno))
-		goto close_prog;
+		goto cleanup;
 
-	link = bpf_program__attach_perf_event(prog, pmu_fd);
-	if (CHECK(IS_ERR(link), "attach_perf_event",
-		  "err %ld\n", PTR_ERR(link))) {
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	if (CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event",
+		  "err %ld\n", PTR_ERR(skel->links.oncpu))) {
 		close(pmu_fd);
-		goto close_prog;
+		goto cleanup;
 	}
 
 	/* find map fds */
-	control_map_fd = bpf_find_map(__func__, obj, "control_map");
-	if (CHECK(control_map_fd < 0, "bpf_find_map control_map",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
-
-	stackid_hmap_fd = bpf_find_map(__func__, obj, "stackid_hmap");
-	if (CHECK(stackid_hmap_fd < 0, "bpf_find_map stackid_hmap",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
-
-	stackmap_fd = bpf_find_map(__func__, obj, "stackmap");
-	if (CHECK(stackmap_fd < 0, "bpf_find_map stackmap", "err %d errno %d\n",
-		  err, errno))
-		goto disable_pmu;
-
-	stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap");
-	if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap",
-		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+	control_map_fd = bpf_map__fd(skel->maps.control_map);
+	stackid_hmap_fd = bpf_map__fd(skel->maps.stackid_hmap);
+	stackmap_fd = bpf_map__fd(skel->maps.stackmap);
 
 	if (CHECK_FAIL(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null")))
-		goto disable_pmu;
+		goto cleanup;
 	if (CHECK_FAIL(system("taskset 0x1 ./urandom_read 100000")))
-		goto disable_pmu;
+		goto cleanup;
 	/* disable stack trace collection */
 	key = 0;
 	val = 1;
@@ -97,23 +86,23 @@ retry:
 	err = compare_map_keys(stackid_hmap_fd, stackmap_fd);
 	if (CHECK(err, "compare_map_keys stackid_hmap vs. stackmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = compare_map_keys(stackmap_fd, stackid_hmap_fd);
 	if (CHECK(err, "compare_map_keys stackmap vs. stackid_hmap",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = extract_build_id(buf, 256);
 
 	if (CHECK(err, "get build_id with readelf",
 		  "err %d errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	err = bpf_map_get_next_key(stackmap_fd, NULL, &key);
 	if (CHECK(err, "get_next_key from stackmap",
 		  "err %d, errno %d\n", err, errno))
-		goto disable_pmu;
+		goto cleanup;
 
 	do {
 		char build_id[64];
@@ -121,7 +110,7 @@ retry:
 		err = bpf_map_lookup_elem(stackmap_fd, &key, id_offs);
 		if (CHECK(err, "lookup_elem from stackmap",
 			  "err %d, errno %d\n", err, errno))
-			goto disable_pmu;
+			goto cleanup;
 		for (i = 0; i < PERF_MAX_STACK_DEPTH; ++i)
 			if (id_offs[i].status == BPF_STACK_BUILD_ID_VALID &&
 			    id_offs[i].offset != 0) {
@@ -139,8 +128,7 @@ retry:
 	 * try it one more time.
 	 */
 	if (build_id_matches < 1 && retry--) {
-		bpf_link__destroy(link);
-		bpf_object__close(obj);
+		test_stacktrace_build_id__destroy(skel);
 		printf("%s:WARN:Didn't find expected build ID from the map, retrying\n",
 		       __func__);
 		goto retry;
@@ -148,7 +136,7 @@ retry:
 
 	if (CHECK(build_id_matches < 1, "build id match",
 		  "Didn't find expected build ID from the map\n"))
-		goto disable_pmu;
+		goto cleanup;
 
 	/*
 	 * We intentionally skip compare_stack_ips(). This is because we
@@ -157,8 +145,6 @@ retry:
 	 * BPF_STACK_BUILD_ID_IP;
 	 */
 
-disable_pmu:
-	bpf_link__destroy(link);
-close_prog:
-	bpf_object__close(obj);
+cleanup:
+	test_stacktrace_build_id__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
new file mode 100644
index 000000000000..25b068591e9a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <test_progs.h>
+
+const char *err_str;
+bool found;
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	char *log_buf;
+
+	if (level != LIBBPF_WARN ||
+	    strcmp(format, "libbpf: \n%s\n")) {
+		vprintf(format, args);
+		return 0;
+	}
+
+	log_buf = va_arg(args, char *);
+	if (!log_buf)
+		goto out;
+	if (strstr(log_buf, err_str) == 0)
+		found = true;
+out:
+	printf(format, log_buf);
+	return 0;
+}
+
+extern int extra_prog_load_log_flags;
+
+static int check_load(const char *file)
+{
+	struct bpf_prog_load_attr attr;
+	struct bpf_object *obj = NULL;
+	int err, prog_fd;
+
+	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+	attr.file = file;
+	attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+	attr.log_level = extra_prog_load_log_flags;
+	attr.prog_flags = BPF_F_TEST_RND_HI32;
+	found = false;
+	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	bpf_object__close(obj);
+	return err;
+}
+
+struct test_def {
+	const char *file;
+	const char *err_str;
+};
+
+void test_test_global_funcs(void)
+{
+	struct test_def tests[] = {
+		{ "test_global_func1.o", "combined stack size of 4 calls is 544" },
+		{ "test_global_func2.o" },
+		{ "test_global_func3.o" , "the call stack of 8 frames" },
+		{ "test_global_func4.o" },
+		{ "test_global_func5.o" , "expected pointer to ctx, but got PTR" },
+		{ "test_global_func6.o" , "modified ctx ptr R2" },
+		{ "test_global_func7.o" , "foo() doesn't return scalar" },
+	};
+	libbpf_print_fn_t old_print_fn = NULL;
+	int err, i, duration = 0;
+
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+	for (i = 0; i < ARRAY_SIZE(tests); i++) {
+		const struct test_def *test = &tests[i];
+
+		if (!test__start_subtest(test->file))
+			continue;
+
+		err_str = test->err_str;
+		err = check_load(test->file);
+		CHECK_FAIL(!!err ^ !!err_str);
+		if (err_str)
+			CHECK(found, "", "expected string '%s'", err_str);
+	}
+	libbpf_set_print(old_print_fn);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/test_overhead.c b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
index c32aa28bd93f..465b371a561d 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_overhead.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_overhead.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 #define _GNU_SOURCE
 #include <sched.h>
+#include <sys/prctl.h>
 #include <test_progs.h>
 
 #define MAX_CNT 100000
@@ -17,7 +18,7 @@ static __u64 time_get_ns(void)
 static int test_task_rename(const char *prog)
 {
 	int i, fd, duration = 0, err;
-	char buf[] = "test\n";
+	char buf[] = "test_overhead";
 	__u64 start_time;
 
 	fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
@@ -66,6 +67,10 @@ void test_test_overhead(void)
 	struct bpf_object *obj;
 	struct bpf_link *link;
 	int err, duration = 0;
+	char comm[16] = {};
+
+	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
+		return;
 
 	obj = bpf_object__open_file("./test_overhead.o", NULL);
 	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
@@ -138,5 +143,6 @@ void test_test_overhead(void)
 	test_run("fexit");
 	bpf_link__destroy(link);
 cleanup:
+	prctl(PR_SET_NAME, comm, 0L, 0L, 0L);
 	bpf_object__close(obj);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
new file mode 100644
index 000000000000..1235f3d1cc50
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#define _GNU_SOURCE
+#include <sched.h>
+#include <sys/prctl.h>
+#include <test_progs.h>
+
+#define MAX_TRAMP_PROGS 40
+
+struct inst {
+	struct bpf_object *obj;
+	struct bpf_link   *link_fentry;
+	struct bpf_link   *link_fexit;
+};
+
+static int test_task_rename(void)
+{
+	int fd, duration = 0, err;
+	char buf[] = "test_overhead";
+
+	fd = open("/proc/self/comm", O_WRONLY|O_TRUNC);
+	if (CHECK(fd < 0, "open /proc", "err %d", errno))
+		return -1;
+	err = write(fd, buf, sizeof(buf));
+	if (err < 0) {
+		CHECK(err < 0, "task rename", "err %d", errno);
+		close(fd);
+		return -1;
+	}
+	close(fd);
+	return 0;
+}
+
+static struct bpf_link *load(struct bpf_object *obj, const char *name)
+{
+	struct bpf_program *prog;
+	int duration = 0;
+
+	prog = bpf_object__find_program_by_title(obj, name);
+	if (CHECK(!prog, "find_probe", "prog '%s' not found\n", name))
+		return ERR_PTR(-EINVAL);
+	return bpf_program__attach_trace(prog);
+}
+
+void test_trampoline_count(void)
+{
+	const char *fentry_name = "fentry/__set_task_comm";
+	const char *fexit_name = "fexit/__set_task_comm";
+	const char *object = "test_trampoline_count.o";
+	struct inst inst[MAX_TRAMP_PROGS] = { 0 };
+	int err, i = 0, duration = 0;
+	struct bpf_object *obj;
+	struct bpf_link *link;
+	char comm[16] = {};
+
+	/* attach 'allowed' 40 trampoline programs */
+	for (i = 0; i < MAX_TRAMP_PROGS; i++) {
+		obj = bpf_object__open_file(object, NULL);
+		if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+			goto cleanup;
+
+		err = bpf_object__load(obj);
+		if (CHECK(err, "obj_load", "err %d\n", err))
+			goto cleanup;
+		inst[i].obj = obj;
+
+		if (rand() % 2) {
+			link = load(obj, fentry_name);
+			if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link)))
+				goto cleanup;
+			inst[i].link_fentry = link;
+		} else {
+			link = load(obj, fexit_name);
+			if (CHECK(IS_ERR(link), "attach prog", "err %ld\n", PTR_ERR(link)))
+				goto cleanup;
+			inst[i].link_fexit = link;
+		}
+	}
+
+	/* and try 1 extra.. */
+	obj = bpf_object__open_file(object, NULL);
+	if (CHECK(IS_ERR(obj), "obj_open_file", "err %ld\n", PTR_ERR(obj)))
+		goto cleanup;
+
+	err = bpf_object__load(obj);
+	if (CHECK(err, "obj_load", "err %d\n", err))
+		goto cleanup_extra;
+
+	/* ..that needs to fail */
+	link = load(obj, fentry_name);
+	if (CHECK(!IS_ERR(link), "cannot attach over the limit", "err %ld\n", PTR_ERR(link))) {
+		bpf_link__destroy(link);
+		goto cleanup_extra;
+	}
+
+	/* with E2BIG error */
+	CHECK(PTR_ERR(link) != -E2BIG, "proper error check", "err %ld\n", PTR_ERR(link));
+
+	/* and finaly execute the probe */
+	if (CHECK_FAIL(prctl(PR_GET_NAME, comm, 0L, 0L, 0L)))
+		goto cleanup_extra;
+	CHECK_FAIL(test_task_rename());
+	CHECK_FAIL(prctl(PR_SET_NAME, comm, 0L, 0L, 0L));
+
+cleanup_extra:
+	bpf_object__close(obj);
+cleanup:
+	while (--i) {
+		bpf_link__destroy(inst[i].link_fentry);
+		bpf_link__destroy(inst[i].link_fexit);
+		bpf_object__close(inst[i].obj);
+	}
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
new file mode 100644
index 000000000000..6b56bdc73ebc
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bpf2bpf.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <net/if.h>
+#include "test_xdp.skel.h"
+#include "test_xdp_bpf2bpf.skel.h"
+
+void test_xdp_bpf2bpf(void)
+{
+	__u32 duration = 0, retval, size;
+	char buf[128];
+	int err, pkt_fd, map_fd;
+	struct iphdr *iph = (void *)buf + sizeof(struct ethhdr);
+	struct iptnl_info value4 = {.family = AF_INET};
+	struct test_xdp *pkt_skel = NULL;
+	struct test_xdp_bpf2bpf *ftrace_skel = NULL;
+	struct vip key4 = {.protocol = 6, .family = AF_INET};
+	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
+
+	/* Load XDP program to introspect */
+	pkt_skel = test_xdp__open_and_load();
+	if (CHECK(!pkt_skel, "pkt_skel_load", "test_xdp skeleton failed\n"))
+		return;
+
+	pkt_fd = bpf_program__fd(pkt_skel->progs._xdp_tx_iptunnel);
+
+	map_fd = bpf_map__fd(pkt_skel->maps.vip2tnl);
+	bpf_map_update_elem(map_fd, &key4, &value4, 0);
+
+	/* Load trace program */
+	opts.attach_prog_fd = pkt_fd,
+	ftrace_skel = test_xdp_bpf2bpf__open_opts(&opts);
+	if (CHECK(!ftrace_skel, "__open", "ftrace skeleton failed\n"))
+		goto out;
+
+	err = test_xdp_bpf2bpf__load(ftrace_skel);
+	if (CHECK(err, "__load", "ftrace skeleton failed\n"))
+		goto out;
+
+	err = test_xdp_bpf2bpf__attach(ftrace_skel);
+	if (CHECK(err, "ftrace_attach", "ftrace attach failed: %d\n", err))
+		goto out;
+
+	/* Run test program */
+	err = bpf_prog_test_run(pkt_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				buf, &size, &retval, &duration);
+
+	if (CHECK(err || retval != XDP_TX || size != 74 ||
+		  iph->protocol != IPPROTO_IPIP, "ipv4",
+		  "err %d errno %d retval %d size %d\n",
+		  err, errno, retval, size))
+		goto out;
+
+	/* Verify test results */
+	if (CHECK(ftrace_skel->bss->test_result_fentry != if_nametoindex("lo"),
+		  "result", "fentry failed err %llu\n",
+		  ftrace_skel->bss->test_result_fentry))
+		goto out;
+
+	CHECK(ftrace_skel->bss->test_result_fexit != XDP_TX, "result",
+	      "fexit failed err %llu\n", ftrace_skel->bss->test_result_fexit);
+
+out:
+	test_xdp__destroy(pkt_skel);
+	test_xdp_bpf2bpf__destroy(ftrace_skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_perf.c b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c
new file mode 100644
index 000000000000..7185bee16fe4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_perf.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_xdp_perf(void)
+{
+	const char *file = "./xdp_dummy.o";
+	__u32 duration, retval, size;
+	struct bpf_object *obj;
+	char in[128], out[128];
+	int err, prog_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd);
+	if (CHECK_FAIL(err))
+		return;
+
+	err = bpf_prog_test_run(prog_fd, 1000000, &in[0], 128,
+				out, &size, &retval, &duration);
+
+	CHECK(err || retval != XDP_PASS || size != 128,
+	      "xdp-perf",
+	      "err %d errno %d retval %d size %d\n",
+	      err, errno, retval, size);
+
+	bpf_object__close(obj);
+}