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

Daniel Borkmann says:

====================
pull-request: bpf-next 2020-08-04

The following pull-request contains BPF updates for your *net-next* tree.

We've added 73 non-merge commits during the last 9 day(s) which contain
a total of 135 files changed, 4603 insertions(+), 1013 deletions(-).

The main changes are:

1) Implement bpf_link support for XDP. Also add LINK_DETACH operation for the BPF
   syscall allowing processes with BPF link FD to force-detach, from Andrii Nakryiko.

2) Add BPF iterator for map elements and to iterate all BPF programs for efficient
   in-kernel inspection, from Yonghong Song and Alexei Starovoitov.

3) Separate bpf_get_{stack,stackid}() helpers for perf events in BPF to avoid
   unwinder errors, from Song Liu.

4) Allow cgroup local storage map to be shared between programs on the same
   cgroup. Also extend BPF selftests with coverage, from YiFei Zhu.

5) Add BPF exception tables to ARM64 JIT in order to be able to JIT BPF_PROBE_MEM
   load instructions, from Jean-Philippe Brucker.

6) Follow-up fixes on BPF socket lookup in combination with reuseport group
   handling. Also add related BPF selftests, from Jakub Sitnicki.

7) Allow to use socket storage in BPF_PROG_TYPE_CGROUP_SOCK-typed programs for
   socket create/release as well as bind functions, from Stanislav Fomichev.

8) Fix an info leak in xsk_getsockopt() when retrieving XDP stats via old struct
   xdp_statistics, from Peilin Ye.

9) Fix PT_REGS_RC{,_CORE}() macros in libbpf for MIPS arch, from Jerry Crunchtime.

10) Extend BPF kernel test infra with skb->family and skb->{local,remote}_ip{4,6}
    fields and allow user space to specify skb->dev via ifindex, from Dmitry Yakunin.

11) Fix a bpftool segfault due to missing program type name and make it more robust
    to prevent them in future gaps, from Quentin Monnet.

12) Consolidate cgroup helper functions across selftests and fix a v6 localhost
    resolver issue, from John Fastabend.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 1339 insertions, 35 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index fed42755416d..4ffefdc1130f 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -15,6 +15,13 @@
 #include "bpf_iter_test_kern2.skel.h"
 #include "bpf_iter_test_kern3.skel.h"
 #include "bpf_iter_test_kern4.skel.h"
+#include "bpf_iter_bpf_hash_map.skel.h"
+#include "bpf_iter_bpf_percpu_hash_map.skel.h"
+#include "bpf_iter_bpf_array_map.skel.h"
+#include "bpf_iter_bpf_percpu_array_map.skel.h"
+#include "bpf_iter_bpf_sk_storage_map.skel.h"
+#include "bpf_iter_test_kern5.skel.h"
+#include "bpf_iter_test_kern6.skel.h"
 
 static int duration;
 
@@ -455,6 +462,440 @@ out:
 	bpf_iter_test_kern4__destroy(skel);
 }
 
+static void test_bpf_hash_map(void)
+{
+	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_hash_map *skel;
+	int err, i, len, map_fd, iter_fd;
+	__u64 val, expected_val = 0;
+	struct bpf_link *link;
+	struct key_t {
+		int a;
+		int b;
+		int c;
+	} key;
+	char buf[64];
+
+	skel = bpf_iter_bpf_hash_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_hash_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->bss->in_test_mode = true;
+
+	err = bpf_iter_bpf_hash_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_hash_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* iterator with hashmap2 and hashmap3 should fail */
+	opts.map_fd = bpf_map__fd(skel->maps.hashmap2);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter",
+		  "attach_iter for hashmap2 unexpected succeeded\n"))
+		goto out;
+
+	opts.map_fd = bpf_map__fd(skel->maps.hashmap3);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter",
+		  "attach_iter for hashmap3 unexpected succeeded\n"))
+		goto out;
+
+	/* hashmap1 should be good, update map values here */
+	map_fd = bpf_map__fd(skel->maps.hashmap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) {
+		key.a = i + 1;
+		key.b = i + 2;
+		key.c = i + 3;
+		val = i + 4;
+		expected_key_a += key.a;
+		expected_key_b += key.b;
+		expected_key_c += key.c;
+		expected_val += val;
+
+		err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	opts.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum_a != expected_key_a,
+		  "key_sum_a", "got %u expected %u\n",
+		  skel->bss->key_sum_a, expected_key_a))
+		goto close_iter;
+	if (CHECK(skel->bss->key_sum_b != expected_key_b,
+		  "key_sum_b", "got %u expected %u\n",
+		  skel->bss->key_sum_b, expected_key_b))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %llu expected %llu\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_hash_map__destroy(skel);
+}
+
+static void test_bpf_percpu_hash_map(void)
+{
+	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_percpu_hash_map *skel;
+	int err, i, j, len, map_fd, iter_fd;
+	__u32 expected_val = 0;
+	struct bpf_link *link;
+	struct key_t {
+		int a;
+		int b;
+		int c;
+	} key;
+	char buf[64];
+	void *val;
+
+	val = malloc(8 * bpf_num_possible_cpus());
+
+	skel = bpf_iter_bpf_percpu_hash_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->rodata->num_cpus = bpf_num_possible_cpus();
+
+	err = bpf_iter_bpf_percpu_hash_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_hash_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* update map values here */
+	map_fd = bpf_map__fd(skel->maps.hashmap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.hashmap1); i++) {
+		key.a = i + 1;
+		key.b = i + 2;
+		key.c = i + 3;
+		expected_key_a += key.a;
+		expected_key_b += key.b;
+		expected_key_c += key.c;
+
+		for (j = 0; j < bpf_num_possible_cpus(); j++) {
+			*(__u32 *)(val + j * 8) = i + j;
+			expected_val += i + j;
+		}
+
+		err = bpf_map_update_elem(map_fd, &key, val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	opts.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_hash_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum_a != expected_key_a,
+		  "key_sum_a", "got %u expected %u\n",
+		  skel->bss->key_sum_a, expected_key_a))
+		goto close_iter;
+	if (CHECK(skel->bss->key_sum_b != expected_key_b,
+		  "key_sum_b", "got %u expected %u\n",
+		  skel->bss->key_sum_b, expected_key_b))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_percpu_hash_map__destroy(skel);
+}
+
+static void test_bpf_array_map(void)
+{
+	__u64 val, expected_val = 0, res_first_val, first_val = 0;
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	__u32 expected_key = 0, res_first_key;
+	struct bpf_iter_bpf_array_map *skel;
+	int err, i, map_fd, iter_fd;
+	struct bpf_link *link;
+	char buf[64] = {};
+	int len, start;
+
+	skel = bpf_iter_bpf_array_map__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_array_map__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.arraymap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		val = i + 4;
+		expected_key += i;
+		expected_val += val;
+
+		if (i == 0)
+			first_val = val;
+
+		err = bpf_map_update_elem(map_fd, &i, &val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	opts.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_array_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	start = 0;
+	while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0)
+		start += len;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	res_first_key = *(__u32 *)buf;
+	res_first_val = *(__u64 *)(buf + sizeof(__u32));
+	if (CHECK(res_first_key != 0 || res_first_val != first_val,
+		  "bpf_seq_write",
+		  "seq_write failure: first key %u vs expected 0, "
+		  " first value %llu vs expected %llu\n",
+		  res_first_key, res_first_val, first_val))
+		goto close_iter;
+
+	if (CHECK(skel->bss->key_sum != expected_key,
+		  "key_sum", "got %u expected %u\n",
+		  skel->bss->key_sum, expected_key))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %llu expected %llu\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		err = bpf_map_lookup_elem(map_fd, &i, &val);
+		if (CHECK(err, "map_lookup", "map_lookup failed\n"))
+			goto out;
+		if (CHECK(i != val, "invalid_val",
+			  "got value %llu expected %u\n", val, i))
+			goto out;
+	}
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_array_map__destroy(skel);
+}
+
+static void test_bpf_percpu_array_map(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_bpf_percpu_array_map *skel;
+	__u32 expected_key = 0, expected_val = 0;
+	int err, i, j, map_fd, iter_fd;
+	struct bpf_link *link;
+	char buf[64];
+	void *val;
+	int len;
+
+	val = malloc(8 * bpf_num_possible_cpus());
+
+	skel = bpf_iter_bpf_percpu_array_map__open();
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__open",
+		  "skeleton open failed\n"))
+		return;
+
+	skel->rodata->num_cpus = bpf_num_possible_cpus();
+
+	err = bpf_iter_bpf_percpu_array_map__load(skel);
+	if (CHECK(!skel, "bpf_iter_bpf_percpu_array_map__load",
+		  "skeleton load failed\n"))
+		goto out;
+
+	/* update map values here */
+	map_fd = bpf_map__fd(skel->maps.arraymap1);
+	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
+		expected_key += i;
+
+		for (j = 0; j < bpf_num_possible_cpus(); j++) {
+			*(__u32 *)(val + j * 8) = i + j;
+			expected_val += i + j;
+		}
+
+		err = bpf_map_update_elem(map_fd, &i, val, BPF_ANY);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	opts.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_percpu_array_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->key_sum != expected_key,
+		  "key_sum", "got %u expected %u\n",
+		  skel->bss->key_sum, expected_key))
+		goto close_iter;
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	bpf_iter_bpf_percpu_array_map__destroy(skel);
+}
+
+static void test_bpf_sk_storage_map(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	int err, i, len, map_fd, iter_fd, num_sockets;
+	struct bpf_iter_bpf_sk_storage_map *skel;
+	int sock_fd[3] = {-1, -1, -1};
+	__u32 val, expected_val = 0;
+	struct bpf_link *link;
+	char buf[64];
+
+	skel = bpf_iter_bpf_sk_storage_map__open_and_load();
+	if (CHECK(!skel, "bpf_iter_bpf_sk_storage_map__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	map_fd = bpf_map__fd(skel->maps.sk_stg_map);
+	num_sockets = ARRAY_SIZE(sock_fd);
+	for (i = 0; i < num_sockets; i++) {
+		sock_fd[i] = socket(AF_INET6, SOCK_STREAM, 0);
+		if (CHECK(sock_fd[i] < 0, "socket", "errno: %d\n", errno))
+			goto out;
+
+		val = i + 1;
+		expected_val += val;
+
+		err = bpf_map_update_elem(map_fd, &sock_fd[i], &val,
+					  BPF_NOEXIST);
+		if (CHECK(err, "map_update", "map_update failed\n"))
+			goto out;
+	}
+
+	opts.map_fd = map_fd;
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_sk_storage_map, &opts);
+	if (CHECK(IS_ERR(link), "attach_iter", "attach_iter failed\n"))
+		goto out;
+
+	iter_fd = bpf_iter_create(bpf_link__fd(link));
+	if (CHECK(iter_fd < 0, "create_iter", "create_iter failed\n"))
+		goto free_link;
+
+	/* do some tests */
+	while ((len = read(iter_fd, buf, sizeof(buf))) > 0)
+		;
+	if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)))
+		goto close_iter;
+
+	/* test results */
+	if (CHECK(skel->bss->ipv6_sk_count != num_sockets,
+		  "ipv6_sk_count", "got %u expected %u\n",
+		  skel->bss->ipv6_sk_count, num_sockets))
+		goto close_iter;
+
+	if (CHECK(skel->bss->val_sum != expected_val,
+		  "val_sum", "got %u expected %u\n",
+		  skel->bss->val_sum, expected_val))
+		goto close_iter;
+
+close_iter:
+	close(iter_fd);
+free_link:
+	bpf_link__destroy(link);
+out:
+	for (i = 0; i < num_sockets; i++) {
+		if (sock_fd[i] >= 0)
+			close(sock_fd[i]);
+	}
+	bpf_iter_bpf_sk_storage_map__destroy(skel);
+}
+
+static void test_rdonly_buf_out_of_bound(void)
+{
+	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
+	struct bpf_iter_test_kern5 *skel;
+	struct bpf_link *link;
+
+	skel = bpf_iter_test_kern5__open_and_load();
+	if (CHECK(!skel, "bpf_iter_test_kern5__open_and_load",
+		  "skeleton open_and_load failed\n"))
+		return;
+
+	opts.map_fd = bpf_map__fd(skel->maps.hashmap1);
+	link = bpf_program__attach_iter(skel->progs.dump_bpf_hash_map, &opts);
+	if (CHECK(!IS_ERR(link), "attach_iter", "unexpected success\n"))
+		bpf_link__destroy(link);
+
+	bpf_iter_test_kern5__destroy(skel);
+}
+
+static void test_buf_neg_offset(void)
+{
+	struct bpf_iter_test_kern6 *skel;
+
+	skel = bpf_iter_test_kern6__open_and_load();
+	if (CHECK(skel, "bpf_iter_test_kern6__open_and_load",
+		  "skeleton open_and_load unexpected success\n"))
+		bpf_iter_test_kern6__destroy(skel);
+}
+
 void test_bpf_iter(void)
 {
 	if (test__start_subtest("btf_id_or_null"))
@@ -491,4 +932,18 @@ void test_bpf_iter(void)
 		test_overflow(true, false);
 	if (test__start_subtest("prog-ret-1"))
 		test_overflow(false, true);
+	if (test__start_subtest("bpf_hash_map"))
+		test_bpf_hash_map();
+	if (test__start_subtest("bpf_percpu_hash_map"))
+		test_bpf_percpu_hash_map();
+	if (test__start_subtest("bpf_array_map"))
+		test_bpf_array_map();
+	if (test__start_subtest("bpf_percpu_array_map"))
+		test_bpf_percpu_array_map();
+	if (test__start_subtest("bpf_sk_storage_map"))
+		test_bpf_sk_storage_map();
+	if (test__start_subtest("rdonly-buf-out-of-bound"))
+		test_rdonly_buf_out_of_bound();
+	if (test__start_subtest("buf-neg-offset"))
+		test_buf_neg_offset();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
new file mode 100644
index 000000000000..643dfa35419c
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -0,0 +1,417 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+/*
+ * Copyright 2020 Google LLC.
+ */
+
+#include <test_progs.h>
+#include <cgroup_helpers.h>
+#include <network_helpers.h>
+
+#include "progs/cg_storage_multi.h"
+
+#include "cg_storage_multi_egress_only.skel.h"
+#include "cg_storage_multi_isolated.skel.h"
+#include "cg_storage_multi_shared.skel.h"
+
+#define PARENT_CGROUP "/cgroup_storage"
+#define CHILD_CGROUP "/cgroup_storage/child"
+
+static int duration;
+
+static bool assert_storage(struct bpf_map *map, const void *key,
+			   struct cgroup_value *expected)
+{
+	struct cgroup_value value;
+	int map_fd;
+
+	map_fd = bpf_map__fd(map);
+
+	if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) < 0,
+		  "map-lookup", "errno %d", errno))
+		return true;
+	if (CHECK(memcmp(&value, expected, sizeof(struct cgroup_value)),
+		  "assert-storage", "storages differ"))
+		return true;
+
+	return false;
+}
+
+static bool assert_storage_noexist(struct bpf_map *map, const void *key)
+{
+	struct cgroup_value value;
+	int map_fd;
+
+	map_fd = bpf_map__fd(map);
+
+	if (CHECK(bpf_map_lookup_elem(map_fd, key, &value) == 0,
+		  "map-lookup", "succeeded, expected ENOENT"))
+		return true;
+	if (CHECK(errno != ENOENT,
+		  "map-lookup", "errno %d, expected ENOENT", errno))
+		return true;
+
+	return false;
+}
+
+static bool connect_send(const char *cgroup_path)
+{
+	bool res = true;
+	int server_fd = -1, client_fd = -1;
+
+	if (join_cgroup(cgroup_path))
+		goto out_clean;
+
+	server_fd = start_server(AF_INET, SOCK_DGRAM, NULL, 0, 0);
+	if (server_fd < 0)
+		goto out_clean;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (client_fd < 0)
+		goto out_clean;
+
+	if (send(client_fd, "message", strlen("message"), 0) < 0)
+		goto out_clean;
+
+	res = false;
+
+out_clean:
+	close(client_fd);
+	close(server_fd);
+	return res;
+}
+
+static void test_egress_only(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_egress_only *obj;
+	struct cgroup_value expected_cgroup_value;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_link *parent_link = NULL, *child_link = NULL;
+	bool err;
+
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+
+	obj = cg_storage_multi_egress_only__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is only one run and in that run the storage is
+	 * parent cgroup's storage.
+	 * Also assert that child cgroup's storage does not exist
+	 */
+	parent_link = bpf_program__attach_cgroup(obj->progs.egress,
+						 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_link), "parent-cg-attach",
+		  "err %ld", PTR_ERR(parent_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 1,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there are two additional runs, one that run with parent
+	 * cgroup's storage and one with child cgroup's storage.
+	 */
+	child_link = bpf_program__attach_cgroup(obj->progs.egress,
+						child_cgroup_fd);
+	if (CHECK(IS_ERR(child_link), "child-cg-attach",
+		  "err %ld", PTR_ERR(child_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_link))
+		bpf_link__destroy(parent_link);
+	if (!IS_ERR(child_link))
+		bpf_link__destroy(child_link);
+
+	cg_storage_multi_egress_only__destroy(obj);
+}
+
+static void test_isolated(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_isolated *obj;
+	struct cgroup_value expected_cgroup_value;
+	struct bpf_cgroup_storage_key key;
+	struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL;
+	struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL;
+	struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL;
+	bool err;
+
+	obj = cg_storage_multi_isolated__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is three runs, two with parent cgroup egress and
+	 * one with parent cgroup ingress, stored in separate parent storages.
+	 * Also assert that child cgroup's storages does not exist
+	 */
+	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress1_link)))
+		goto close_bpf_object;
+	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress2_link)))
+		goto close_bpf_object;
+	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
+		  "err %ld", PTR_ERR(parent_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there is six additional runs, parent cgroup egresses and
+	 * ingress, child cgroup egresses and ingress.
+	 * Assert that egree and ingress storages are separate.
+	 */
+	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
+		  "err %ld", PTR_ERR(child_egress1_link)))
+		goto close_bpf_object;
+	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
+		  "err %ld", PTR_ERR(child_egress2_link)))
+		goto close_bpf_object;
+	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
+		  "err %ld", PTR_ERR(child_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 9,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(PARENT_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 4 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.cgroup_inode_id = get_cgroup_id(CHILD_CGROUP);
+	key.attach_type = BPF_CGROUP_INET_EGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .egress_pkts = 2 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key.attach_type = BPF_CGROUP_INET_INGRESS;
+	expected_cgroup_value = (struct cgroup_value) { .ingress_pkts = 1 };
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_egress1_link))
+		bpf_link__destroy(parent_egress1_link);
+	if (!IS_ERR(parent_egress2_link))
+		bpf_link__destroy(parent_egress2_link);
+	if (!IS_ERR(parent_ingress_link))
+		bpf_link__destroy(parent_ingress_link);
+	if (!IS_ERR(child_egress1_link))
+		bpf_link__destroy(child_egress1_link);
+	if (!IS_ERR(child_egress2_link))
+		bpf_link__destroy(child_egress2_link);
+	if (!IS_ERR(child_ingress_link))
+		bpf_link__destroy(child_ingress_link);
+
+	cg_storage_multi_isolated__destroy(obj);
+}
+
+static void test_shared(int parent_cgroup_fd, int child_cgroup_fd)
+{
+	struct cg_storage_multi_shared *obj;
+	struct cgroup_value expected_cgroup_value;
+	__u64 key;
+	struct bpf_link *parent_egress1_link = NULL, *parent_egress2_link = NULL;
+	struct bpf_link *child_egress1_link = NULL, *child_egress2_link = NULL;
+	struct bpf_link *parent_ingress_link = NULL, *child_ingress_link = NULL;
+	bool err;
+
+	obj = cg_storage_multi_shared__open_and_load();
+	if (CHECK(!obj, "skel-load", "errno %d", errno))
+		return;
+
+	/* Attach to parent cgroup, trigger packet from child.
+	 * Assert that there is three runs, two with parent cgroup egress and
+	 * one with parent cgroup ingress.
+	 * Also assert that child cgroup's storage does not exist
+	 */
+	parent_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress1_link), "parent-egress1-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress1_link)))
+		goto close_bpf_object;
+	parent_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_egress2_link), "parent-egress2-cg-attach",
+		  "err %ld", PTR_ERR(parent_egress2_link)))
+		goto close_bpf_object;
+	parent_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							 parent_cgroup_fd);
+	if (CHECK(IS_ERR(parent_ingress_link), "parent-ingress-cg-attach",
+		  "err %ld", PTR_ERR(parent_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "first-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 3,
+		  "first-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 2,
+		.ingress_pkts = 1,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key = get_cgroup_id(CHILD_CGROUP);
+	if (assert_storage_noexist(obj->maps.cgroup_storage, &key))
+		goto close_bpf_object;
+
+	/* Attach to parent and child cgroup, trigger packet from child.
+	 * Assert that there is six additional runs, parent cgroup egresses and
+	 * ingress, child cgroup egresses and ingress.
+	 */
+	child_egress1_link = bpf_program__attach_cgroup(obj->progs.egress1,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress1_link), "child-egress1-cg-attach",
+		  "err %ld", PTR_ERR(child_egress1_link)))
+		goto close_bpf_object;
+	child_egress2_link = bpf_program__attach_cgroup(obj->progs.egress2,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_egress2_link), "child-egress2-cg-attach",
+		  "err %ld", PTR_ERR(child_egress2_link)))
+		goto close_bpf_object;
+	child_ingress_link = bpf_program__attach_cgroup(obj->progs.ingress,
+							child_cgroup_fd);
+	if (CHECK(IS_ERR(child_ingress_link), "child-ingress-cg-attach",
+		  "err %ld", PTR_ERR(child_ingress_link)))
+		goto close_bpf_object;
+	err = connect_send(CHILD_CGROUP);
+	if (CHECK(err, "second-connect-send", "errno %d", errno))
+		goto close_bpf_object;
+	if (CHECK(obj->bss->invocations != 9,
+		  "second-invoke", "invocations=%d", obj->bss->invocations))
+		goto close_bpf_object;
+	key = get_cgroup_id(PARENT_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 4,
+		.ingress_pkts = 2,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+	key = get_cgroup_id(CHILD_CGROUP);
+	expected_cgroup_value = (struct cgroup_value) {
+		.egress_pkts = 2,
+		.ingress_pkts = 1,
+	};
+	if (assert_storage(obj->maps.cgroup_storage,
+			   &key, &expected_cgroup_value))
+		goto close_bpf_object;
+
+close_bpf_object:
+	if (!IS_ERR(parent_egress1_link))
+		bpf_link__destroy(parent_egress1_link);
+	if (!IS_ERR(parent_egress2_link))
+		bpf_link__destroy(parent_egress2_link);
+	if (!IS_ERR(parent_ingress_link))
+		bpf_link__destroy(parent_ingress_link);
+	if (!IS_ERR(child_egress1_link))
+		bpf_link__destroy(child_egress1_link);
+	if (!IS_ERR(child_egress2_link))
+		bpf_link__destroy(child_egress2_link);
+	if (!IS_ERR(child_ingress_link))
+		bpf_link__destroy(child_ingress_link);
+
+	cg_storage_multi_shared__destroy(obj);
+}
+
+void test_cg_storage_multi(void)
+{
+	int parent_cgroup_fd = -1, child_cgroup_fd = -1;
+
+	parent_cgroup_fd = test__join_cgroup(PARENT_CGROUP);
+	if (CHECK(parent_cgroup_fd < 0, "cg-create-parent", "errno %d", errno))
+		goto close_cgroup_fd;
+	child_cgroup_fd = create_and_get_cgroup(CHILD_CGROUP);
+	if (CHECK(child_cgroup_fd < 0, "cg-create-child", "errno %d", errno))
+		goto close_cgroup_fd;
+
+	if (test__start_subtest("egress_only"))
+		test_egress_only(parent_cgroup_fd, child_cgroup_fd);
+
+	if (test__start_subtest("isolated"))
+		test_isolated(parent_cgroup_fd, child_cgroup_fd);
+
+	if (test__start_subtest("shared"))
+		test_shared(parent_cgroup_fd, child_cgroup_fd);
+
+close_cgroup_fd:
+	close(child_cgroup_fd);
+	close(parent_cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 6e04f8d1d15b..4d9b514b3fd9 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -2,6 +2,7 @@
 
 #include <test_progs.h>
 #include "cgroup_helpers.h"
+#include "testing_helpers.h"
 #include "test_cgroup_link.skel.h"
 
 static __u32 duration = 0;
@@ -37,7 +38,8 @@ void test_cgroup_link(void)
 	int last_cg = ARRAY_SIZE(cgs) - 1, cg_nr = ARRAY_SIZE(cgs);
 	DECLARE_LIBBPF_OPTS(bpf_link_update_opts, link_upd_opts);
 	struct bpf_link *links[ARRAY_SIZE(cgs)] = {}, *tmp_link;
-	__u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags;
+	__u32 prog_ids[ARRAY_SIZE(cgs)], prog_cnt = 0, attach_flags, prog_id;
+	struct bpf_link_info info;
 	int i = 0, err, prog_fd;
 	bool detach_legacy = false;
 
@@ -219,6 +221,22 @@ void test_cgroup_link(void)
 	/* BPF programs should still get called */
 	ping_and_check(0, cg_nr);
 
+	prog_id = link_info_prog_id(links[0], &info);
+	CHECK(prog_id == 0, "link_info", "failed\n");
+	CHECK(info.cgroup.cgroup_id == 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id);
+
+	err = bpf_link__detach(links[0]);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto cleanup;
+
+	/* cgroup_id should be zero in link_info */
+	prog_id = link_info_prog_id(links[0], &info);
+	CHECK(prog_id == 0, "link_info", "failed\n");
+	CHECK(info.cgroup.cgroup_id != 0, "cgroup_id", "unexpected %llu\n", info.cgroup.cgroup_id);
+
+	/* First BPF program shouldn't be called anymore */
+	ping_and_check(0, cg_nr - 1);
+
 	/* leave cgroup and remove them, don't detach programs */
 	cleanup_cgroup_environment();
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_retro.c b/tools/testing/selftests/bpf/prog_tests/core_retro.c
index 78e30d3a23d5..6acb0e94d4d7 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_retro.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_retro.c
@@ -6,7 +6,7 @@
 
 void test_core_retro(void)
 {
-	int err, zero = 0, res, duration = 0;
+	int err, zero = 0, res, duration = 0, my_pid = getpid();
 	struct test_core_retro *skel;
 
 	/* load program */
@@ -14,6 +14,10 @@ void test_core_retro(void)
 	if (CHECK(!skel, "skel_load", "skeleton open/load failed\n"))
 		goto out_close;
 
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.exp_tgid_map), &zero, &my_pid, 0);
+	if (CHECK(err, "map_update", "failed to set expected PID: %d\n", errno))
+		goto out_close;
+
 	/* attach probe */
 	err = test_core_retro__attach(skel);
 	if (CHECK(err, "attach_kprobe", "err %d\n", err))
@@ -26,7 +30,7 @@ void test_core_retro(void)
 	if (CHECK(err, "map_lookup", "failed to lookup result: %d\n", errno))
 		goto out_close;
 
-	CHECK(res != getpid(), "pid_check", "got %d != exp %d\n", res, getpid());
+	CHECK(res != my_pid, "pid_check", "got %d != exp %d\n", res, my_pid);
 
 out_close:
 	test_core_retro__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
new file mode 100644
index 000000000000..d884b2ed5bc5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_stackid_cannot_attach.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#include <test_progs.h>
+#include "test_stacktrace_build_id.skel.h"
+
+void test_get_stackid_cannot_attach(void)
+{
+	struct perf_event_attr attr = {
+		/* .type = PERF_TYPE_SOFTWARE, */
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.precise_ip = 1,
+		.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK,
+		.branch_sample_type = PERF_SAMPLE_BRANCH_USER |
+			PERF_SAMPLE_BRANCH_NO_FLAGS |
+			PERF_SAMPLE_BRANCH_NO_CYCLES |
+			PERF_SAMPLE_BRANCH_CALL_STACK,
+		.sample_period = 5000,
+		.size = sizeof(struct perf_event_attr),
+	};
+	struct test_stacktrace_build_id *skel;
+	__u32 duration = 0;
+	int pmu_fd, err;
+
+	skel = test_stacktrace_build_id__open();
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
+		return;
+
+	/* 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 (pmu_fd < 0 && (errno == ENOENT || errno == EOPNOTSUPP)) {
+		printf("%s:SKIP:cannot open PERF_COUNT_HW_CPU_CYCLES with precise_ip > 0\n",
+		       __func__);
+		test__skip();
+		goto cleanup;
+	}
+	if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_no_callchain",
+	      "should have failed\n");
+	close(pmu_fd);
+
+	/* add PERF_SAMPLE_CALLCHAIN, attach should succeed */
+	attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+
+	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\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(IS_ERR(skel->links.oncpu), "attach_perf_event_callchain",
+	      "err: %ld\n", PTR_ERR(skel->links.oncpu));
+	close(pmu_fd);
+
+	/* add exclude_callchain_kernel, attach should fail */
+	attr.exclude_callchain_kernel = 1;
+
+	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\n",
+		  pmu_fd, errno))
+		goto cleanup;
+
+	skel->links.oncpu = bpf_program__attach_perf_event(skel->progs.oncpu,
+							   pmu_fd);
+	CHECK(!IS_ERR(skel->links.oncpu), "attach_perf_event_exclude_callchain_kernel",
+	      "should have failed\n");
+	close(pmu_fd);
+
+cleanup:
+	test_stacktrace_build_id__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
new file mode 100644
index 000000000000..72c3690844fb
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/perf_event_stackmap.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2020 Facebook
+#define _GNU_SOURCE
+#include <pthread.h>
+#include <sched.h>
+#include <test_progs.h>
+#include "perf_event_stackmap.skel.h"
+
+#ifndef noinline
+#define noinline __attribute__((noinline))
+#endif
+
+noinline int func_1(void)
+{
+	static int val = 1;
+
+	val += 1;
+
+	usleep(100);
+	return val;
+}
+
+noinline int func_2(void)
+{
+	return func_1();
+}
+
+noinline int func_3(void)
+{
+	return func_2();
+}
+
+noinline int func_4(void)
+{
+	return func_3();
+}
+
+noinline int func_5(void)
+{
+	return func_4();
+}
+
+noinline int func_6(void)
+{
+	int i, val = 1;
+
+	for (i = 0; i < 100; i++)
+		val += func_5();
+
+	return val;
+}
+
+void test_perf_event_stackmap(void)
+{
+	struct perf_event_attr attr = {
+		/* .type = PERF_TYPE_SOFTWARE, */
+		.type = PERF_TYPE_HARDWARE,
+		.config = PERF_COUNT_HW_CPU_CYCLES,
+		.precise_ip = 2,
+		.sample_type = PERF_SAMPLE_IP | PERF_SAMPLE_BRANCH_STACK |
+			PERF_SAMPLE_CALLCHAIN,
+		.branch_sample_type = PERF_SAMPLE_BRANCH_USER |
+			PERF_SAMPLE_BRANCH_NO_FLAGS |
+			PERF_SAMPLE_BRANCH_NO_CYCLES |
+			PERF_SAMPLE_BRANCH_CALL_STACK,
+		.sample_period = 5000,
+		.size = sizeof(struct perf_event_attr),
+	};
+	struct perf_event_stackmap *skel;
+	__u32 duration = 0;
+	cpu_set_t cpu_set;
+	int pmu_fd, err;
+
+	skel = perf_event_stackmap__open();
+
+	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
+		return;
+
+	err = perf_event_stackmap__load(skel);
+	if (CHECK(err, "skel_load", "skeleton load failed: %d\n", err))
+		goto cleanup;
+
+	CPU_ZERO(&cpu_set);
+	CPU_SET(0, &cpu_set);
+	err = pthread_setaffinity_np(pthread_self(), sizeof(cpu_set), &cpu_set);
+	if (CHECK(err, "set_affinity", "err %d, errno %d\n", err, errno))
+		goto cleanup;
+
+	pmu_fd = syscall(__NR_perf_event_open, &attr, -1 /* pid */,
+			 0 /* cpu 0 */, -1 /* group id */,
+			 0 /* flags */);
+	if (pmu_fd < 0) {
+		printf("%s:SKIP:cpu doesn't support the event\n", __func__);
+		test__skip();
+		goto cleanup;
+	}
+
+	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 cleanup;
+	}
+
+	/* create kernel and user stack traces for testing */
+	func_6();
+
+	CHECK(skel->data->stackid_kernel != 2, "get_stackid_kernel", "failed\n");
+	CHECK(skel->data->stackid_user != 2, "get_stackid_user", "failed\n");
+	CHECK(skel->data->stack_kernel != 2, "get_stack_kernel", "failed\n");
+	CHECK(skel->data->stack_user != 2, "get_stack_user", "failed\n");
+
+cleanup:
+	perf_event_stackmap__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/section_names.c b/tools/testing/selftests/bpf/prog_tests/section_names.c
index 713167449c98..8b571890c57e 100644
--- a/tools/testing/selftests/bpf/prog_tests/section_names.c
+++ b/tools/testing/selftests/bpf/prog_tests/section_names.c
@@ -35,7 +35,7 @@ static struct sec_name_test tests[] = {
 		{-EINVAL, 0},
 	},
 	{"raw_tp/", {0, BPF_PROG_TYPE_RAW_TRACEPOINT, 0}, {-EINVAL, 0} },
-	{"xdp", {0, BPF_PROG_TYPE_XDP, 0}, {-EINVAL, 0} },
+	{"xdp", {0, BPF_PROG_TYPE_XDP, BPF_XDP}, {0, BPF_XDP} },
 	{"perf_event", {0, BPF_PROG_TYPE_PERF_EVENT, 0}, {-EINVAL, 0} },
 	{"lwt_in", {0, BPF_PROG_TYPE_LWT_IN, 0}, {-EINVAL, 0} },
 	{"lwt_out", {0, BPF_PROG_TYPE_LWT_OUT, 0}, {-EINVAL, 0} },
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index f1784ae4565a..c571584c00f5 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -34,6 +34,7 @@
 #include "bpf_util.h"
 #include "cgroup_helpers.h"
 #include "network_helpers.h"
+#include "testing_helpers.h"
 #include "test_sk_lookup.skel.h"
 
 /* External (address, port) pairs the client sends packets to. */
@@ -74,6 +75,7 @@ struct test {
 	struct inet_addr connect_to;
 	struct inet_addr listen_at;
 	enum server accept_on;
+	bool reuseport_has_conns; /* Add a connected socket to reuseport group */
 };
 
 static __u32 duration;		/* for CHECK macro */
@@ -468,34 +470,10 @@ static int update_lookup_map(struct bpf_map *map, int index, int sock_fd)
 	return 0;
 }
 
-static __u32 link_info_prog_id(struct bpf_link *link)
-{
-	struct bpf_link_info info = {};
-	__u32 info_len = sizeof(info);
-	int link_fd, err;
-
-	link_fd = bpf_link__fd(link);
-	if (CHECK(link_fd < 0, "bpf_link__fd", "failed\n")) {
-		errno = -link_fd;
-		log_err("bpf_link__fd failed");
-		return 0;
-	}
-
-	err = bpf_obj_get_info_by_fd(link_fd, &info, &info_len);
-	if (CHECK(err, "bpf_obj_get_info_by_fd", "failed\n")) {
-		log_err("bpf_obj_get_info_by_fd");
-		return 0;
-	}
-	if (CHECK(info_len != sizeof(info), "bpf_obj_get_info_by_fd",
-		  "unexpected info len %u\n", info_len))
-		return 0;
-
-	return info.prog_id;
-}
-
 static void query_lookup_prog(struct test_sk_lookup *skel)
 {
 	struct bpf_link *link[3] = {};
+	struct bpf_link_info info;
 	__u32 attach_flags = 0;
 	__u32 prog_ids[3] = {};
 	__u32 prog_cnt = 3;
@@ -533,18 +511,36 @@ static void query_lookup_prog(struct test_sk_lookup *skel)
 	if (CHECK(prog_cnt != 3, "bpf_prog_query",
 		  "wrong program count on query: %u", prog_cnt))
 		goto detach;
-	prog_id = link_info_prog_id(link[0]);
+	prog_id = link_info_prog_id(link[0], &info);
 	CHECK(prog_ids[0] != prog_id, "bpf_prog_query",
 	      "invalid program #0 id on query: %u != %u\n",
 	      prog_ids[0], prog_id);
-	prog_id = link_info_prog_id(link[1]);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+	prog_id = link_info_prog_id(link[1], &info);
 	CHECK(prog_ids[1] != prog_id, "bpf_prog_query",
 	      "invalid program #1 id on query: %u != %u\n",
 	      prog_ids[1], prog_id);
-	prog_id = link_info_prog_id(link[2]);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+	prog_id = link_info_prog_id(link[2], &info);
 	CHECK(prog_ids[2] != prog_id, "bpf_prog_query",
 	      "invalid program #2 id on query: %u != %u\n",
 	      prog_ids[2], prog_id);
+	CHECK(info.netns.netns_ino == 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
+
+	err = bpf_link__detach(link[0]);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto detach;
+
+	/* prog id is still there, but netns_ino is zeroed out */
+	prog_id = link_info_prog_id(link[0], &info);
+	CHECK(prog_ids[0] != prog_id, "bpf_prog_query",
+	      "invalid program #0 id on query: %u != %u\n",
+	      prog_ids[0], prog_id);
+	CHECK(info.netns.netns_ino != 0, "netns_ino",
+	      "unexpected netns_ino: %u\n", info.netns.netns_ino);
 
 detach:
 	if (link[2])
@@ -559,7 +555,8 @@ close:
 
 static void run_lookup_prog(const struct test *t)
 {
-	int client_fd, server_fds[MAX_SERVERS] = { -1 };
+	int server_fds[MAX_SERVERS] = { -1 };
+	int client_fd, reuse_conn_fd = -1;
 	struct bpf_link *lookup_link;
 	int i, err;
 
@@ -583,6 +580,32 @@ static void run_lookup_prog(const struct test *t)
 			break;
 	}
 
+	/* Regular UDP socket lookup with reuseport behaves
+	 * differently when reuseport group contains connected
+	 * sockets. Check that adding a connected UDP socket to the
+	 * reuseport group does not affect how reuseport works with
+	 * BPF socket lookup.
+	 */
+	if (t->reuseport_has_conns) {
+		struct sockaddr_storage addr = {};
+		socklen_t len = sizeof(addr);
+
+		/* Add an extra socket to reuseport group */
+		reuse_conn_fd = make_server(t->sotype, t->listen_at.ip,
+					    t->listen_at.port,
+					    t->reuseport_prog);
+		if (reuse_conn_fd < 0)
+			goto close;
+
+		/* Connect the extra socket to itself */
+		err = getsockname(reuse_conn_fd, (void *)&addr, &len);
+		if (CHECK(err, "getsockname", "errno %d\n", errno))
+			goto close;
+		err = connect(reuse_conn_fd, (void *)&addr, len);
+		if (CHECK(err, "connect", "errno %d\n", errno))
+			goto close;
+	}
+
 	client_fd = make_client(t->sotype, t->connect_to.ip, t->connect_to.port);
 	if (client_fd < 0)
 		goto close;
@@ -594,6 +617,8 @@ static void run_lookup_prog(const struct test *t)
 
 	close(client_fd);
 close:
+	if (reuse_conn_fd != -1)
+		close(reuse_conn_fd);
 	for (i = 0; i < ARRAY_SIZE(server_fds); i++) {
 		if (server_fds[i] != -1)
 			close(server_fds[i]);
@@ -711,6 +736,17 @@ static void test_redirect_lookup(struct test_sk_lookup *skel)
 			.accept_on	= SERVER_B,
 		},
 		{
+			.desc		= "UDP IPv4 redir and reuseport with conns",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP4, EXT_PORT },
+			.listen_at	= { INT_IP4, INT_PORT },
+			.accept_on	= SERVER_B,
+			.reuseport_has_conns = true,
+		},
+		{
 			.desc		= "UDP IPv4 redir skip reuseport",
 			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
 			.reuseport_prog	= skel->progs.select_sock_b,
@@ -755,6 +791,17 @@ static void test_redirect_lookup(struct test_sk_lookup *skel)
 			.accept_on	= SERVER_B,
 		},
 		{
+			.desc		= "UDP IPv6 redir and reuseport with conns",
+			.lookup_prog	= skel->progs.select_sock_a,
+			.reuseport_prog	= skel->progs.select_sock_b,
+			.sock_map	= skel->maps.redir_map,
+			.sotype		= SOCK_DGRAM,
+			.connect_to	= { EXT_IP6, EXT_PORT },
+			.listen_at	= { INT_IP6, INT_PORT },
+			.accept_on	= SERVER_B,
+			.reuseport_has_conns = true,
+		},
+		{
 			.desc		= "UDP IPv6 redir skip reuseport",
 			.lookup_prog	= skel->progs.select_sock_a_no_reuseport,
 			.reuseport_prog	= skel->progs.select_sock_b,
@@ -1238,8 +1285,8 @@ static void run_tests(struct test_sk_lookup *skel)
 static int switch_netns(void)
 {
 	static const char * const setup_script[] = {
-		"ip -6 addr add dev lo " EXT_IP6 "/128 nodad",
-		"ip -6 addr add dev lo " INT_IP6 "/128 nodad",
+		"ip -6 addr add dev lo " EXT_IP6 "/128",
+		"ip -6 addr add dev lo " INT_IP6 "/128",
 		"ip link set dev lo up",
 		NULL,
 	};
diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index 7021b92af313..25de86af2d03 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -11,6 +11,7 @@ void test_skb_ctx(void)
 		.cb[3] = 4,
 		.cb[4] = 5,
 		.priority = 6,
+		.ifindex = 1,
 		.tstamp = 7,
 		.wire_len = 100,
 		.gso_segs = 8,
@@ -92,6 +93,10 @@ void test_skb_ctx(void)
 		   "ctx_out_priority",
 		   "skb->priority == %d, expected %d\n",
 		   skb.priority, 7);
+	CHECK_ATTR(skb.ifindex != 1,
+		   "ctx_out_ifindex",
+		   "skb->ifindex == %d, expected %d\n",
+		   skb.ifindex, 1);
 	CHECK_ATTR(skb.tstamp != 8,
 		   "ctx_out_tstamp",
 		   "skb->tstamp == %lld, expected %d\n",
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
new file mode 100644
index 000000000000..6f814999b395
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2020 Facebook */
+#include <uapi/linux/if_link.h>
+#include <test_progs.h>
+#include "test_xdp_link.skel.h"
+
+#define IFINDEX_LO 1
+
+void test_xdp_link(void)
+{
+	__u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
+	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
+	struct test_xdp_link *skel1 = NULL, *skel2 = NULL;
+	struct bpf_link_info link_info;
+	struct bpf_prog_info prog_info;
+	struct bpf_link *link;
+	__u32 link_info_len = sizeof(link_info);
+	__u32 prog_info_len = sizeof(prog_info);
+
+	skel1 = test_xdp_link__open_and_load();
+	if (CHECK(!skel1, "skel_load", "skeleton open and load failed\n"))
+		goto cleanup;
+	prog_fd1 = bpf_program__fd(skel1->progs.xdp_handler);
+
+	skel2 = test_xdp_link__open_and_load();
+	if (CHECK(!skel2, "skel_load", "skeleton open and load failed\n"))
+		goto cleanup;
+	prog_fd2 = bpf_program__fd(skel2->progs.xdp_handler);
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	err = bpf_obj_get_info_by_fd(prog_fd1, &prog_info, &prog_info_len);
+	if (CHECK(err, "fd_info1", "failed %d\n", -errno))
+		goto cleanup;
+	id1 = prog_info.id;
+
+	memset(&prog_info, 0, sizeof(prog_info));
+	err = bpf_obj_get_info_by_fd(prog_fd2, &prog_info, &prog_info_len);
+	if (CHECK(err, "fd_info2", "failed %d\n", -errno))
+		goto cleanup;
+	id2 = prog_info.id;
+
+	/* set initial prog attachment */
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd1, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(err, "fd_attach", "initial prog attach failed: %d\n", err))
+		goto cleanup;
+
+	/* validate prog ID */
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	CHECK(err || id0 != id1, "id1_check",
+	      "loaded prog id %u != id1 %u, err %d", id0, id1, err);
+
+	/* BPF link is not allowed to replace prog attachment */
+	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+		bpf_link__destroy(link);
+		/* best-effort detach prog */
+		opts.old_fd = prog_fd1;
+		bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
+		goto cleanup;
+	}
+
+	/* detach BPF program */
+	opts.old_fd = prog_fd1;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, -1, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(err, "prog_detach", "failed %d\n", err))
+		goto cleanup;
+
+	/* now BPF link should attach successfully */
+	link = bpf_program__attach_xdp(skel1->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+	skel1->links.xdp_handler = link;
+
+	/* validate prog ID */
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id1, "id1_check",
+		  "loaded prog id %u != id1 %u, err %d", id0, id1, err))
+		goto cleanup;
+
+	/* BPF prog attach is not allowed to replace BPF link */
+	opts.old_fd = prog_fd1;
+	err = bpf_set_link_xdp_fd_opts(IFINDEX_LO, prog_fd2, XDP_FLAGS_REPLACE, &opts);
+	if (CHECK(!err, "prog_attach_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* Can't force-update when BPF link is active */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, prog_fd2, 0);
+	if (CHECK(!err, "prog_update_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* Can't force-detach when BPF link is active */
+	err = bpf_set_link_xdp_fd(IFINDEX_LO, -1, 0);
+	if (CHECK(!err, "prog_detach_fail", "unexpected success\n"))
+		goto cleanup;
+
+	/* BPF link is not allowed to replace another BPF link */
+	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(!IS_ERR(link), "link_attach_fail", "unexpected success\n")) {
+		bpf_link__destroy(link);
+		goto cleanup;
+	}
+
+	bpf_link__destroy(skel1->links.xdp_handler);
+	skel1->links.xdp_handler = NULL;
+
+	/* new link attach should succeed */
+	link = bpf_program__attach_xdp(skel2->progs.xdp_handler, IFINDEX_LO);
+	if (CHECK(IS_ERR(link), "link_attach", "failed: %ld\n", PTR_ERR(link)))
+		goto cleanup;
+	skel2->links.xdp_handler = link;
+
+	err = bpf_get_link_xdp_id(IFINDEX_LO, &id0, 0);
+	if (CHECK(err || id0 != id2, "id2_check",
+		  "loaded prog id %u != id2 %u, err %d", id0, id1, err))
+		goto cleanup;
+
+	/* updating program under active BPF link works as expected */
+	err = bpf_link__update_program(link, skel1->progs.xdp_handler);
+	if (CHECK(err, "link_upd", "failed: %d\n", err))
+		goto cleanup;
+
+	memset(&link_info, 0, sizeof(link_info));
+	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	if (CHECK(err, "link_info", "failed: %d\n", err))
+		goto cleanup;
+
+	CHECK(link_info.type != BPF_LINK_TYPE_XDP, "link_type",
+	      "got %u != exp %u\n", link_info.type, BPF_LINK_TYPE_XDP);
+	CHECK(link_info.prog_id != id1, "link_prog_id",
+	      "got %u != exp %u\n", link_info.prog_id, id1);
+	CHECK(link_info.xdp.ifindex != IFINDEX_LO, "link_ifindex",
+	      "got %u != exp %u\n", link_info.xdp.ifindex, IFINDEX_LO);
+
+	err = bpf_link__detach(link);
+	if (CHECK(err, "link_detach", "failed %d\n", err))
+		goto cleanup;
+
+	memset(&link_info, 0, sizeof(link_info));
+	err = bpf_obj_get_info_by_fd(bpf_link__fd(link), &link_info, &link_info_len);
+	if (CHECK(err, "link_info", "failed: %d\n", err))
+		goto cleanup;
+	CHECK(link_info.prog_id != id1, "link_prog_id",
+	      "got %u != exp %u\n", link_info.prog_id, id1);
+	/* ifindex should be zeroed out */
+	CHECK(link_info.xdp.ifindex != 0, "link_ifindex",
+	      "got %u != exp %u\n", link_info.xdp.ifindex, 0);
+
+cleanup:
+	test_xdp_link__destroy(skel1);
+	test_xdp_link__destroy(skel2);
+}