Merge branch 'sk-local-storage'

Martin KaFai Lau says:

====================
v4:
- Move checks to map_alloc_check in patch 1 (Stanislav Fomichev)
- Refactor BTF encoding macros to test_btf.h at
  a new patch 4 (Stanislav Fomichev)
- Refactor getenv and add print PASS message at the
  end of the test in patch 6 (Yonghong Song)

v3:
- Replace spinlock_types.h with spinlock.h in patch 1
  (kbuild test robot <lkp@intel.com>)

v2:
- Add the "test_maps.h" file in patch 5

This series introduces the BPF sk local storage.  The
details is in the patch 1 commit message.
====================

Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

11 files changed, 1058 insertions, 107 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f9d83ba7843e..66f2dca1dee1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -74,6 +74,8 @@ all: $(TEST_CUSTOM_PROGS)
 $(OUTPUT)/urandom_read: $(OUTPUT)/%: %.c
 	$(CC) -o $@ $< -Wl,--build-id
 
+$(OUTPUT)/test_maps: map_tests/*.c
+
 BPFOBJ := $(OUTPUT)/libbpf.a
 
 $(TEST_GEN_PROGS): $(BPFOBJ)
@@ -232,6 +234,27 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
 		  echo '#endif' \
 		 ) > $(PROG_TESTS_H))
 
+TEST_MAPS_CFLAGS := -I. -I$(OUTPUT)
+MAP_TESTS_DIR = $(OUTPUT)/map_tests
+$(MAP_TESTS_DIR):
+	mkdir -p $@
+MAP_TESTS_H := $(MAP_TESTS_DIR)/tests.h
+test_maps.c: $(MAP_TESTS_H)
+$(OUTPUT)/test_maps: CFLAGS += $(TEST_MAPS_CFLAGS)
+MAP_TESTS_FILES := $(wildcard map_tests/*.c)
+$(MAP_TESTS_H): $(MAP_TESTS_DIR) $(MAP_TESTS_FILES)
+	$(shell ( cd map_tests/; \
+		  echo '/* Generated header, do not edit */'; \
+		  echo '#ifdef DECLARE'; \
+		  ls *.c 2> /dev/null | \
+			sed -e 's@\([^\.]*\)\.c@extern void test_\1(void);@'; \
+		  echo '#endif'; \
+		  echo '#ifdef CALL'; \
+		  ls *.c 2> /dev/null | \
+			sed -e 's@\([^\.]*\)\.c@test_\1();@'; \
+		  echo '#endif' \
+		 ) > $(MAP_TESTS_H))
+
 VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
 test_verifier.c: $(VERIFIER_TESTS_H)
 $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
@@ -251,4 +274,4 @@ $(OUTPUT)/verifier/tests.h: $(VERIFIER_TESTS_DIR) $(VERIFIER_TEST_FILES)
 		 ) > $(VERIFIER_TESTS_H))
 
 EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(ALU32_BUILD_DIR) \
-	$(VERIFIER_TESTS_H) $(PROG_TESTS_H)
+	$(VERIFIER_TESTS_H) $(PROG_TESTS_H) $(MAP_TESTS_H)
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 59e221586cf7..6e80b66d7fb1 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -211,6 +211,11 @@ static int (*bpf_strtol)(const char *buf, unsigned long long buf_len,
 static int (*bpf_strtoul)(const char *buf, unsigned long long buf_len,
 			  unsigned long long flags, unsigned long *res) =
 	(void *) BPF_FUNC_strtoul;
+static void *(*bpf_sk_storage_get)(void *map, struct bpf_sock *sk,
+				   void *value, __u64 flags) =
+	(void *) BPF_FUNC_sk_storage_get;
+static int (*bpf_sk_storage_delete)(void *map, struct bpf_sock *sk) =
+	(void *)BPF_FUNC_sk_storage_delete;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
new file mode 100644
index 000000000000..e569edc679d8
--- /dev/null
+++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2019 Facebook  */
+#include <linux/compiler.h>
+#include <linux/err.h>
+
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <linux/btf.h>
+#include <unistd.h>
+#include <signal.h>
+#include <errno.h>
+#include <string.h>
+#include <pthread.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include <test_btf.h>
+#include <test_maps.h>
+
+static struct bpf_create_map_attr xattr = {
+	.name = "sk_storage_map",
+	.map_type = BPF_MAP_TYPE_SK_STORAGE,
+	.map_flags = BPF_F_NO_PREALLOC,
+	.max_entries = 0,
+	.key_size = 4,
+	.value_size = 8,
+	.btf_key_type_id = 1,
+	.btf_value_type_id = 3,
+	.btf_fd = -1,
+};
+
+static unsigned int nr_sk_threads_done;
+static unsigned int nr_sk_threads_err;
+static unsigned int nr_sk_per_thread = 4096;
+static unsigned int nr_sk_threads = 4;
+static int sk_storage_map = -1;
+static unsigned int stop;
+static int runtime_s = 5;
+
+static bool is_stopped(void)
+{
+	return READ_ONCE(stop);
+}
+
+static unsigned int threads_err(void)
+{
+	return READ_ONCE(nr_sk_threads_err);
+}
+
+static void notify_thread_err(void)
+{
+	__sync_add_and_fetch(&nr_sk_threads_err, 1);
+}
+
+static bool wait_for_threads_err(void)
+{
+	while (!is_stopped() && !threads_err())
+		usleep(500);
+
+	return !is_stopped();
+}
+
+static unsigned int threads_done(void)
+{
+	return READ_ONCE(nr_sk_threads_done);
+}
+
+static void notify_thread_done(void)
+{
+	__sync_add_and_fetch(&nr_sk_threads_done, 1);
+}
+
+static void notify_thread_redo(void)
+{
+	__sync_sub_and_fetch(&nr_sk_threads_done, 1);
+}
+
+static bool wait_for_threads_done(void)
+{
+	while (threads_done() != nr_sk_threads && !is_stopped() &&
+	       !threads_err())
+		usleep(50);
+
+	return !is_stopped() && !threads_err();
+}
+
+static bool wait_for_threads_redo(void)
+{
+	while (threads_done() && !is_stopped() && !threads_err())
+		usleep(50);
+
+	return !is_stopped() && !threads_err();
+}
+
+static bool wait_for_map(void)
+{
+	while (READ_ONCE(sk_storage_map) == -1 && !is_stopped())
+		usleep(50);
+
+	return !is_stopped();
+}
+
+static bool wait_for_map_close(void)
+{
+	while (READ_ONCE(sk_storage_map) != -1 && !is_stopped())
+		;
+
+	return !is_stopped();
+}
+
+static int load_btf(void)
+{
+	const char btf_str_sec[] = "\0bpf_spin_lock\0val\0cnt\0l";
+	__u32 btf_raw_types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* struct bpf_spin_lock */                      /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 4),
+		BTF_MEMBER_ENC(15, 1, 0), /* int val; */
+		/* struct val */                                /* [3] */
+		BTF_TYPE_ENC(15, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8),
+		BTF_MEMBER_ENC(19, 1, 0), /* int cnt; */
+		BTF_MEMBER_ENC(23, 2, 32),/* struct bpf_spin_lock l; */
+	};
+	struct btf_header btf_hdr = {
+		.magic = BTF_MAGIC,
+		.version = BTF_VERSION,
+		.hdr_len = sizeof(struct btf_header),
+		.type_len = sizeof(btf_raw_types),
+		.str_off = sizeof(btf_raw_types),
+		.str_len = sizeof(btf_str_sec),
+	};
+	__u8 raw_btf[sizeof(struct btf_header) + sizeof(btf_raw_types) +
+		     sizeof(btf_str_sec)];
+
+	memcpy(raw_btf, &btf_hdr, sizeof(btf_hdr));
+	memcpy(raw_btf + sizeof(btf_hdr), btf_raw_types, sizeof(btf_raw_types));
+	memcpy(raw_btf + sizeof(btf_hdr) + sizeof(btf_raw_types),
+	       btf_str_sec, sizeof(btf_str_sec));
+
+	return bpf_load_btf(raw_btf, sizeof(raw_btf), 0, 0, 0);
+}
+
+static int create_sk_storage_map(void)
+{
+	int btf_fd, map_fd;
+
+	btf_fd = load_btf();
+	CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n",
+	      btf_fd, errno);
+	xattr.btf_fd = btf_fd;
+
+	map_fd = bpf_create_map_xattr(&xattr);
+	xattr.btf_fd = -1;
+	close(btf_fd);
+	CHECK(map_fd == -1,
+	      "bpf_create_map_xattr()", "errno:%d\n", errno);
+
+	return map_fd;
+}
+
+static void *insert_close_thread(void *arg)
+{
+	struct {
+		int cnt;
+		int lock;
+	} value = { .cnt = 0xeB9F, .lock = 0, };
+	int i, map_fd, err, *sk_fds;
+
+	sk_fds = malloc(sizeof(*sk_fds) * nr_sk_per_thread);
+	if (!sk_fds) {
+		notify_thread_err();
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0; i < nr_sk_per_thread; i++)
+		sk_fds[i] = -1;
+
+	while (!is_stopped()) {
+		if (!wait_for_map())
+			goto close_all;
+
+		map_fd = READ_ONCE(sk_storage_map);
+		for (i = 0; i < nr_sk_per_thread && !is_stopped(); i++) {
+			sk_fds[i] = socket(AF_INET6, SOCK_STREAM, 0);
+			if (sk_fds[i] == -1) {
+				err = -errno;
+				fprintf(stderr, "socket(): errno:%d\n", errno);
+				goto errout;
+			}
+			err = bpf_map_update_elem(map_fd, &sk_fds[i], &value,
+						  BPF_NOEXIST);
+			if (err) {
+				err = -errno;
+				fprintf(stderr,
+					"bpf_map_update_elem(): errno:%d\n",
+					errno);
+				goto errout;
+			}
+		}
+
+		notify_thread_done();
+		wait_for_map_close();
+
+close_all:
+		for (i = 0; i < nr_sk_per_thread; i++) {
+			close(sk_fds[i]);
+			sk_fds[i] = -1;
+		}
+
+		notify_thread_redo();
+	}
+
+	free(sk_fds);
+	return NULL;
+
+errout:
+	for (i = 0; i < nr_sk_per_thread && sk_fds[i] != -1; i++)
+		close(sk_fds[i]);
+	free(sk_fds);
+	notify_thread_err();
+	return ERR_PTR(err);
+}
+
+static int do_sk_storage_map_stress_free(void)
+{
+	int i, map_fd = -1, err = 0, nr_threads_created = 0;
+	pthread_t *sk_thread_ids;
+	void *thread_ret;
+
+	sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads);
+	if (!sk_thread_ids) {
+		fprintf(stderr, "malloc(sk_threads): NULL\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nr_sk_threads; i++) {
+		err = pthread_create(&sk_thread_ids[i], NULL,
+				     insert_close_thread, NULL);
+		if (err) {
+			err = -errno;
+			goto done;
+		}
+		nr_threads_created++;
+	}
+
+	while (!is_stopped()) {
+		map_fd = create_sk_storage_map();
+		WRITE_ONCE(sk_storage_map, map_fd);
+
+		if (!wait_for_threads_done())
+			break;
+
+		WRITE_ONCE(sk_storage_map, -1);
+		close(map_fd);
+		map_fd = -1;
+
+		if (!wait_for_threads_redo())
+			break;
+	}
+
+done:
+	WRITE_ONCE(stop, 1);
+	for (i = 0; i < nr_threads_created; i++) {
+		pthread_join(sk_thread_ids[i], &thread_ret);
+		if (IS_ERR(thread_ret) && !err) {
+			err = PTR_ERR(thread_ret);
+			fprintf(stderr, "threads#%u: err:%d\n", i, err);
+		}
+	}
+	free(sk_thread_ids);
+
+	if (map_fd != -1)
+		close(map_fd);
+
+	return err;
+}
+
+static void *update_thread(void *arg)
+{
+	struct {
+		int cnt;
+		int lock;
+	} value = { .cnt = 0xeB9F, .lock = 0, };
+	int map_fd = READ_ONCE(sk_storage_map);
+	int sk_fd = *(int *)arg;
+	int err = 0; /* Suppress compiler false alarm */
+
+	while (!is_stopped()) {
+		err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+		if (err && errno != EAGAIN) {
+			err = -errno;
+			fprintf(stderr, "bpf_map_update_elem: %d %d\n",
+				err, errno);
+			break;
+		}
+	}
+
+	if (!is_stopped()) {
+		notify_thread_err();
+		return ERR_PTR(err);
+	}
+
+	return NULL;
+}
+
+static void *delete_thread(void *arg)
+{
+	int map_fd = READ_ONCE(sk_storage_map);
+	int sk_fd = *(int *)arg;
+	int err = 0; /* Suppress compiler false alarm */
+
+	while (!is_stopped()) {
+		err = bpf_map_delete_elem(map_fd, &sk_fd);
+		if (err && errno != ENOENT) {
+			err = -errno;
+			fprintf(stderr, "bpf_map_delete_elem: %d %d\n",
+				err, errno);
+			break;
+		}
+	}
+
+	if (!is_stopped()) {
+		notify_thread_err();
+		return ERR_PTR(err);
+	}
+
+	return NULL;
+}
+
+static int do_sk_storage_map_stress_change(void)
+{
+	int i, sk_fd, map_fd = -1, err = 0, nr_threads_created = 0;
+	pthread_t *sk_thread_ids;
+	void *thread_ret;
+
+	sk_thread_ids = malloc(sizeof(pthread_t) * nr_sk_threads);
+	if (!sk_thread_ids) {
+		fprintf(stderr, "malloc(sk_threads): NULL\n");
+		return -ENOMEM;
+	}
+
+	sk_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (sk_fd == -1) {
+		err = -errno;
+		goto done;
+	}
+
+	map_fd = create_sk_storage_map();
+	WRITE_ONCE(sk_storage_map, map_fd);
+
+	for (i = 0; i < nr_sk_threads; i++) {
+		if (i & 0x1)
+			err = pthread_create(&sk_thread_ids[i], NULL,
+					     update_thread, &sk_fd);
+		else
+			err = pthread_create(&sk_thread_ids[i], NULL,
+					     delete_thread, &sk_fd);
+		if (err) {
+			err = -errno;
+			goto done;
+		}
+		nr_threads_created++;
+	}
+
+	wait_for_threads_err();
+
+done:
+	WRITE_ONCE(stop, 1);
+	for (i = 0; i < nr_threads_created; i++) {
+		pthread_join(sk_thread_ids[i], &thread_ret);
+		if (IS_ERR(thread_ret) && !err) {
+			err = PTR_ERR(thread_ret);
+			fprintf(stderr, "threads#%u: err:%d\n", i, err);
+		}
+	}
+	free(sk_thread_ids);
+
+	if (sk_fd != -1)
+		close(sk_fd);
+	close(map_fd);
+
+	return err;
+}
+
+static void stop_handler(int signum)
+{
+	if (signum != SIGALRM)
+		printf("stopping...\n");
+	WRITE_ONCE(stop, 1);
+}
+
+#define BPF_SK_STORAGE_MAP_TEST_NR_THREADS "BPF_SK_STORAGE_MAP_TEST_NR_THREADS"
+#define BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD "BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD"
+#define BPF_SK_STORAGE_MAP_TEST_RUNTIME_S "BPF_SK_STORAGE_MAP_TEST_RUNTIME_S"
+#define BPF_SK_STORAGE_MAP_TEST_NAME "BPF_SK_STORAGE_MAP_TEST_NAME"
+
+static void test_sk_storage_map_stress_free(void)
+{
+	struct rlimit rlim_old, rlim_new = {};
+	int err;
+
+	getrlimit(RLIMIT_NOFILE, &rlim_old);
+
+	signal(SIGTERM, stop_handler);
+	signal(SIGINT, stop_handler);
+	if (runtime_s > 0) {
+		signal(SIGALRM, stop_handler);
+		alarm(runtime_s);
+	}
+
+	if (rlim_old.rlim_cur < nr_sk_threads * nr_sk_per_thread) {
+		rlim_new.rlim_cur = nr_sk_threads * nr_sk_per_thread + 128;
+		rlim_new.rlim_max = rlim_new.rlim_cur + 128;
+		err = setrlimit(RLIMIT_NOFILE, &rlim_new);
+		CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d",
+		      rlim_new.rlim_cur, errno);
+	}
+
+	err = do_sk_storage_map_stress_free();
+
+	signal(SIGTERM, SIG_DFL);
+	signal(SIGINT, SIG_DFL);
+	if (runtime_s > 0) {
+		signal(SIGALRM, SIG_DFL);
+		alarm(0);
+	}
+
+	if (rlim_new.rlim_cur)
+		setrlimit(RLIMIT_NOFILE, &rlim_old);
+
+	CHECK(err, "test_sk_storage_map_stress_free", "err:%d\n", err);
+}
+
+static void test_sk_storage_map_stress_change(void)
+{
+	int err;
+
+	signal(SIGTERM, stop_handler);
+	signal(SIGINT, stop_handler);
+	if (runtime_s > 0) {
+		signal(SIGALRM, stop_handler);
+		alarm(runtime_s);
+	}
+
+	err = do_sk_storage_map_stress_change();
+
+	signal(SIGTERM, SIG_DFL);
+	signal(SIGINT, SIG_DFL);
+	if (runtime_s > 0) {
+		signal(SIGALRM, SIG_DFL);
+		alarm(0);
+	}
+
+	CHECK(err, "test_sk_storage_map_stress_change", "err:%d\n", err);
+}
+
+static void test_sk_storage_map_basic(void)
+{
+	struct {
+		int cnt;
+		int lock;
+	} value = { .cnt = 0xeB9f, .lock = 0, }, lookup_value;
+	struct bpf_create_map_attr bad_xattr;
+	int btf_fd, map_fd, sk_fd, err;
+
+	btf_fd = load_btf();
+	CHECK(btf_fd == -1, "bpf_load_btf", "btf_fd:%d errno:%d\n",
+	      btf_fd, errno);
+	xattr.btf_fd = btf_fd;
+
+	sk_fd = socket(AF_INET6, SOCK_STREAM, 0);
+	CHECK(sk_fd == -1, "socket()", "sk_fd:%d errno:%d\n",
+	      sk_fd, errno);
+
+	map_fd = bpf_create_map_xattr(&xattr);
+	CHECK(map_fd == -1, "bpf_create_map_xattr(good_xattr)",
+	      "map_fd:%d errno:%d\n", map_fd, errno);
+
+	/* Add new elem */
+	memcpy(&lookup_value, &value, sizeof(value));
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value,
+				  BPF_NOEXIST | BPF_F_LOCK);
+	CHECK(err, "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(err || lookup_value.cnt != value.cnt,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d cnt:%x(%x)\n",
+	      err, errno, lookup_value.cnt, value.cnt);
+
+	/* Bump the cnt and update with BPF_EXIST | BPF_F_LOCK */
+	value.cnt += 1;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value,
+				  BPF_EXIST | BPF_F_LOCK);
+	CHECK(err, "bpf_map_update_elem(BPF_EXIST|BPF_F_LOCK)",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(err || lookup_value.cnt != value.cnt,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d cnt:%x(%x)\n",
+	      err, errno, lookup_value.cnt, value.cnt);
+
+	/* Bump the cnt and update with BPF_EXIST */
+	value.cnt += 1;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_EXIST);
+	CHECK(err, "bpf_map_update_elem(BPF_EXIST)",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(err || lookup_value.cnt != value.cnt,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d cnt:%x(%x)\n",
+	      err, errno, lookup_value.cnt, value.cnt);
+
+	/* Update with BPF_NOEXIST */
+	value.cnt += 1;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value,
+				  BPF_NOEXIST | BPF_F_LOCK);
+	CHECK(!err || errno != EEXIST,
+	      "bpf_map_update_elem(BPF_NOEXIST|BPF_F_LOCK)",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, BPF_NOEXIST);
+	CHECK(!err || errno != EEXIST, "bpf_map_update_elem(BPF_NOEXIST)",
+	      "err:%d errno:%d\n", err, errno);
+	value.cnt -= 1;
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(err || lookup_value.cnt != value.cnt,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d cnt:%x(%x)\n",
+	      err, errno, lookup_value.cnt, value.cnt);
+
+	/* Bump the cnt again and update with map_flags == 0 */
+	value.cnt += 1;
+	err = bpf_map_update_elem(map_fd, &sk_fd, &value, 0);
+	CHECK(err, "bpf_map_update_elem()", "err:%d errno:%d\n",
+	      err, errno);
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(err || lookup_value.cnt != value.cnt,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d cnt:%x(%x)\n",
+	      err, errno, lookup_value.cnt, value.cnt);
+
+	/* Test delete elem */
+	err = bpf_map_delete_elem(map_fd, &sk_fd);
+	CHECK(err, "bpf_map_delete_elem()", "err:%d errno:%d\n",
+	      err, errno);
+	err = bpf_map_lookup_elem_flags(map_fd, &sk_fd, &lookup_value,
+					BPF_F_LOCK);
+	CHECK(!err || errno != ENOENT,
+	      "bpf_map_lookup_elem_flags(BPF_F_LOCK)",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_delete_elem(map_fd, &sk_fd);
+	CHECK(!err || errno != ENOENT, "bpf_map_delete_elem()",
+	      "err:%d errno:%d\n", err, errno);
+
+	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	bad_xattr.btf_key_type_id = 0;
+	err = bpf_create_map_xattr(&bad_xattr);
+	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	      "err:%d errno:%d\n", err, errno);
+
+	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	bad_xattr.btf_key_type_id = 3;
+	err = bpf_create_map_xattr(&bad_xattr);
+	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	      "err:%d errno:%d\n", err, errno);
+
+	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	bad_xattr.max_entries = 1;
+	err = bpf_create_map_xattr(&bad_xattr);
+	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	      "err:%d errno:%d\n", err, errno);
+
+	memcpy(&bad_xattr, &xattr, sizeof(xattr));
+	bad_xattr.map_flags = 0;
+	err = bpf_create_map_xattr(&bad_xattr);
+	CHECK(!err || errno != EINVAL, "bap_create_map_xattr(bad_xattr)",
+	      "err:%d errno:%d\n", err, errno);
+
+	xattr.btf_fd = -1;
+	close(btf_fd);
+	close(map_fd);
+	close(sk_fd);
+}
+
+void test_sk_storage_map(void)
+{
+	const char *test_name, *env_opt;
+	bool test_ran = false;
+
+	test_name = getenv(BPF_SK_STORAGE_MAP_TEST_NAME);
+
+	env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_NR_THREADS);
+	if (env_opt)
+		nr_sk_threads = atoi(env_opt);
+
+	env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_SK_PER_THREAD);
+	if (env_opt)
+		nr_sk_per_thread = atoi(env_opt);
+
+	env_opt = getenv(BPF_SK_STORAGE_MAP_TEST_RUNTIME_S);
+	if (env_opt)
+		runtime_s = atoi(env_opt);
+
+	if (!test_name || !strcmp(test_name, "basic")) {
+		test_sk_storage_map_basic();
+		test_ran = true;
+	}
+	if (!test_name || !strcmp(test_name, "stress_free")) {
+		test_sk_storage_map_stress_free();
+		test_ran = true;
+	}
+	if (!test_name || !strcmp(test_name, "stress_change")) {
+		test_sk_storage_map_stress_change();
+		test_ran = true;
+	}
+
+	if (test_ran)
+		printf("%s:PASS\n", __func__);
+	else
+		CHECK(1, "Invalid test_name", "%s\n", test_name);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
index 37328f148538..1c39e4ccb7f1 100644
--- a/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sock_fields_kern.c
@@ -55,6 +55,31 @@ struct bpf_map_def SEC("maps") linum_map = {
 	.max_entries = __NR_BPF_LINUM_ARRAY_IDX,
 };
 
+struct bpf_spinlock_cnt {
+	struct bpf_spin_lock lock;
+	__u32 cnt;
+};
+
+struct bpf_map_def SEC("maps") sk_pkt_out_cnt = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(struct bpf_spinlock_cnt),
+	.max_entries = 0,
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+
+BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt, int, struct bpf_spinlock_cnt);
+
+struct bpf_map_def SEC("maps") sk_pkt_out_cnt10 = {
+	.type = BPF_MAP_TYPE_SK_STORAGE,
+	.key_size = sizeof(int),
+	.value_size = sizeof(struct bpf_spinlock_cnt),
+	.max_entries = 0,
+	.map_flags = BPF_F_NO_PREALLOC,
+};
+
+BPF_ANNOTATE_KV_PAIR(sk_pkt_out_cnt10, int, struct bpf_spinlock_cnt);
+
 static bool is_loopback6(__u32 *a6)
 {
 	return !a6[0] && !a6[1] && !a6[2] && a6[3] == bpf_htonl(1);
@@ -120,7 +145,9 @@ static void tpcpy(struct bpf_tcp_sock *dst,
 SEC("cgroup_skb/egress")
 int egress_read_sock_fields(struct __sk_buff *skb)
 {
+	struct bpf_spinlock_cnt cli_cnt_init = { .lock = 0, .cnt = 0xeB9F };
 	__u32 srv_idx = ADDR_SRV_IDX, cli_idx = ADDR_CLI_IDX, result_idx;
+	struct bpf_spinlock_cnt *pkt_out_cnt, *pkt_out_cnt10;
 	struct sockaddr_in6 *srv_sa6, *cli_sa6;
 	struct bpf_tcp_sock *tp, *tp_ret;
 	struct bpf_sock *sk, *sk_ret;
@@ -161,6 +188,32 @@ int egress_read_sock_fields(struct __sk_buff *skb)
 	skcpy(sk_ret, sk);
 	tpcpy(tp_ret, tp);
 
+	if (result_idx == EGRESS_SRV_IDX) {
+		/* The userspace has created it for srv sk */
+		pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk, 0, 0);
+		pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10, sk,
+						   0, 0);
+	} else {
+		pkt_out_cnt = bpf_sk_storage_get(&sk_pkt_out_cnt, sk,
+						 &cli_cnt_init,
+						 BPF_SK_STORAGE_GET_F_CREATE);
+		pkt_out_cnt10 = bpf_sk_storage_get(&sk_pkt_out_cnt10,
+						   sk, &cli_cnt_init,
+						   BPF_SK_STORAGE_GET_F_CREATE);
+	}
+
+	if (!pkt_out_cnt || !pkt_out_cnt10)
+		RETURN;
+
+	/* Even both cnt and cnt10 have lock defined in their BTF,
+	 * intentionally one cnt takes lock while one does not
+	 * as a test for the spinlock support in BPF_MAP_TYPE_SK_STORAGE.
+	 */
+	pkt_out_cnt->cnt += 1;
+	bpf_spin_lock(&pkt_out_cnt10->lock);
+	pkt_out_cnt10->cnt += 10;
+	bpf_spin_unlock(&pkt_out_cnt10->lock);
+
 	RETURN;
 }
 
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index f8eb7987b794..42c1ce988945 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -24,6 +24,7 @@
 
 #include "bpf_rlimit.h"
 #include "bpf_util.h"
+#include "test_btf.h"
 
 #define MAX_INSNS	512
 #define MAX_SUBPROGS	16
@@ -58,68 +59,6 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)),
 	return vfprintf(stderr, format, args);
 }
 
-#define BTF_INFO_ENC(kind, kind_flag, vlen)			\
-	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
-
-#define BTF_TYPE_ENC(name, info, size_or_type)	\
-	(name), (info), (size_or_type)
-
-#define BTF_INT_ENC(encoding, bits_offset, nr_bits)	\
-	((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
-#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz)	\
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz),	\
-	BTF_INT_ENC(encoding, bits_offset, bits)
-
-#define BTF_FWD_ENC(name, kind_flag) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0)
-
-#define BTF_ARRAY_ENC(type, index_type, nr_elems)	\
-	(type), (index_type), (nr_elems)
-#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \
-	BTF_ARRAY_ENC(type, index_type, nr_elems)
-
-#define BTF_STRUCT_ENC(name, nr_elems, sz)	\
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz)
-
-#define BTF_UNION_ENC(name, nr_elems, sz)	\
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz)
-
-#define BTF_VAR_ENC(name, type, linkage)	\
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage)
-#define BTF_VAR_SECINFO_ENC(type, offset, size)	\
-	(type), (offset), (size)
-
-#define BTF_MEMBER_ENC(name, type, bits_offset)	\
-	(name), (type), (bits_offset)
-#define BTF_ENUM_ENC(name, val) (name), (val)
-#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
-	((bitfield_size) << 24 | (bits_offset))
-
-#define BTF_TYPEDEF_ENC(name, type) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
-
-#define BTF_PTR_ENC(type) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
-
-#define BTF_CONST_ENC(type) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
-
-#define BTF_VOLATILE_ENC(type) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type)
-
-#define BTF_RESTRICT_ENC(type) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type)
-
-#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
-	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
-
-#define BTF_FUNC_PROTO_ARG_ENC(name, type) \
-	(name), (type)
-
-#define BTF_FUNC_ENC(name, func_proto) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
-
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
 
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
new file mode 100644
index 000000000000..2023725f1962
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 Facebook */
+
+#ifndef _TEST_BTF_H
+#define _TEST_BTF_H
+
+#define BTF_INFO_ENC(kind, kind_flag, vlen)			\
+	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
+
+#define BTF_TYPE_ENC(name, info, size_or_type)	\
+	(name), (info), (size_or_type)
+
+#define BTF_INT_ENC(encoding, bits_offset, nr_bits)	\
+	((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
+#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz),	\
+	BTF_INT_ENC(encoding, bits_offset, bits)
+
+#define BTF_FWD_ENC(name, kind_flag) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FWD, kind_flag, 0), 0)
+
+#define BTF_ARRAY_ENC(type, index_type, nr_elems)	\
+	(type), (index_type), (nr_elems)
+#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \
+	BTF_ARRAY_ENC(type, index_type, nr_elems)
+
+#define BTF_STRUCT_ENC(name, nr_elems, sz)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, nr_elems), sz)
+
+#define BTF_UNION_ENC(name, nr_elems, sz)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz)
+
+#define BTF_VAR_ENC(name, type, linkage)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage)
+#define BTF_VAR_SECINFO_ENC(type, offset, size)	\
+	(type), (offset), (size)
+
+#define BTF_MEMBER_ENC(name, type, bits_offset)	\
+	(name), (type), (bits_offset)
+#define BTF_ENUM_ENC(name, val) (name), (val)
+#define BTF_MEMBER_OFFSET(bitfield_size, bits_offset) \
+	((bitfield_size) << 24 | (bits_offset))
+
+#define BTF_TYPEDEF_ENC(name, type) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type)
+
+#define BTF_PTR_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type)
+
+#define BTF_CONST_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), type)
+
+#define BTF_VOLATILE_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), type)
+
+#define BTF_RESTRICT_ENC(type) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_RESTRICT, 0, 0), type)
+
+#define BTF_FUNC_PROTO_ENC(ret_type, nargs) \
+	BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_FUNC_PROTO, 0, nargs), ret_type)
+
+#define BTF_FUNC_PROTO_ARG_ENC(name, type) \
+	(name), (type)
+
+#define BTF_FUNC_ENC(name, func_proto) \
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FUNC, 0, 0), func_proto)
+
+#endif /* _TEST_BTF_H */
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 3c627771f965..246f745cb006 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -27,6 +27,7 @@
 
 #include "bpf_util.h"
 #include "bpf_rlimit.h"
+#include "test_maps.h"
 
 #ifndef ENOTSUPP
 #define ENOTSUPP 524
@@ -36,15 +37,6 @@ static int skips;
 
 static int map_flags;
 
-#define CHECK(condition, tag, format...) ({				\
-	int __ret = !!(condition);					\
-	if (__ret) {							\
-		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
-		printf(format);						\
-		exit(-1);						\
-	}								\
-})
-
 static void test_hashmap(unsigned int task, void *data)
 {
 	long long key, next_key, first_key, value;
@@ -1703,6 +1695,10 @@ static void run_all_tests(void)
 	test_map_in_map();
 }
 
+#define DECLARE
+#include <map_tests/tests.h>
+#undef DECLARE
+
 int main(void)
 {
 	srand(time(NULL));
@@ -1713,6 +1709,10 @@ int main(void)
 	map_flags = BPF_F_NO_PREALLOC;
 	run_all_tests();
 
+#define CALL
+#include <map_tests/tests.h>
+#undef CALL
+
 	printf("test_maps: OK, %d SKIPPED\n", skips);
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/test_maps.h b/tools/testing/selftests/bpf/test_maps.h
new file mode 100644
index 000000000000..77d8587ac4ed
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_maps.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _TEST_MAPS_H
+#define _TEST_MAPS_H
+
+#include <stdio.h>
+#include <stdlib.h>
+
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
+		printf(format);						\
+		exit(-1);						\
+	}								\
+})
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_sock_fields.c b/tools/testing/selftests/bpf/test_sock_fields.c
index dcae7f664dce..e089477fa0a3 100644
--- a/tools/testing/selftests/bpf/test_sock_fields.c
+++ b/tools/testing/selftests/bpf/test_sock_fields.c
@@ -35,6 +35,11 @@ enum bpf_linum_array_idx {
 	__NR_BPF_LINUM_ARRAY_IDX,
 };
 
+struct bpf_spinlock_cnt {
+	struct bpf_spin_lock lock;
+	__u32 cnt;
+};
+
 #define CHECK(condition, tag, format...) ({				\
 	int __ret = !!(condition);					\
 	if (__ret) {							\
@@ -50,6 +55,8 @@ enum bpf_linum_array_idx {
 #define DATA_LEN sizeof(DATA)
 
 static struct sockaddr_in6 srv_sa6, cli_sa6;
+static int sk_pkt_out_cnt10_fd;
+static int sk_pkt_out_cnt_fd;
 static int linum_map_fd;
 static int addr_map_fd;
 static int tp_map_fd;
@@ -220,28 +227,90 @@ static void check_result(void)
 	      "Unexpected listen_tp", "Check listen_tp output. ingress_linum:%u",
 	      ingress_linum);
 
-	CHECK(srv_tp.data_segs_out != 1 ||
+	CHECK(srv_tp.data_segs_out != 2 ||
 	      srv_tp.data_segs_in ||
 	      srv_tp.snd_cwnd != 10 ||
 	      srv_tp.total_retrans ||
-	      srv_tp.bytes_acked != DATA_LEN,
+	      srv_tp.bytes_acked != 2 * DATA_LEN,
 	      "Unexpected srv_tp", "Check srv_tp output. egress_linum:%u",
 	      egress_linum);
 
 	CHECK(cli_tp.data_segs_out ||
-	      cli_tp.data_segs_in != 1 ||
+	      cli_tp.data_segs_in != 2 ||
 	      cli_tp.snd_cwnd != 10 ||
 	      cli_tp.total_retrans ||
-	      cli_tp.bytes_received != DATA_LEN,
+	      cli_tp.bytes_received != 2 * DATA_LEN,
 	      "Unexpected cli_tp", "Check cli_tp output. egress_linum:%u",
 	      egress_linum);
 }
 
+static void check_sk_pkt_out_cnt(int accept_fd, int cli_fd)
+{
+	struct bpf_spinlock_cnt pkt_out_cnt = {}, pkt_out_cnt10 = {};
+	int err;
+
+	pkt_out_cnt.cnt = ~0;
+	pkt_out_cnt10.cnt = ~0;
+	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &accept_fd, &pkt_out_cnt);
+	if (!err)
+		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &accept_fd,
+					  &pkt_out_cnt10);
+
+	/* The bpf prog only counts for fullsock and
+	 * passive conneciton did not become fullsock until 3WHS
+	 * had been finished.
+	 * The bpf prog only counted two data packet out but we
+	 * specially init accept_fd's pkt_out_cnt by 2 in
+	 * init_sk_storage().  Hence, 4 here.
+	 */
+	CHECK(err || pkt_out_cnt.cnt != 4 || pkt_out_cnt10.cnt != 40,
+	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &accept_fd)",
+	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u",
+	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
+
+	pkt_out_cnt.cnt = ~0;
+	pkt_out_cnt10.cnt = ~0;
+	err = bpf_map_lookup_elem(sk_pkt_out_cnt_fd, &cli_fd, &pkt_out_cnt);
+	if (!err)
+		err = bpf_map_lookup_elem(sk_pkt_out_cnt10_fd, &cli_fd,
+					  &pkt_out_cnt10);
+	/* Active connection is fullsock from the beginning.
+	 * 1 SYN and 1 ACK during 3WHS
+	 * 2 Acks on data packet.
+	 *
+	 * The bpf_prog initialized it to 0xeB9F.
+	 */
+	CHECK(err || pkt_out_cnt.cnt != 0xeB9F + 4 ||
+	      pkt_out_cnt10.cnt != 0xeB9F + 40,
+	      "bpf_map_lookup_elem(sk_pkt_out_cnt, &cli_fd)",
+	      "err:%d errno:%d pkt_out_cnt:%u pkt_out_cnt10:%u",
+	      err, errno, pkt_out_cnt.cnt, pkt_out_cnt10.cnt);
+}
+
+static void init_sk_storage(int sk_fd, __u32 pkt_out_cnt)
+{
+	struct bpf_spinlock_cnt scnt = {};
+	int err;
+
+	scnt.cnt = pkt_out_cnt;
+	err = bpf_map_update_elem(sk_pkt_out_cnt_fd, &sk_fd, &scnt,
+				  BPF_NOEXIST);
+	CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt_fd)",
+	      "err:%d errno:%d", err, errno);
+
+	scnt.cnt *= 10;
+	err = bpf_map_update_elem(sk_pkt_out_cnt10_fd, &sk_fd, &scnt,
+				  BPF_NOEXIST);
+	CHECK(err, "bpf_map_update_elem(sk_pkt_out_cnt10_fd)",
+	      "err:%d errno:%d", err, errno);
+}
+
 static void test(void)
 {
 	int listen_fd, cli_fd, accept_fd, epfd, err;
 	struct epoll_event ev;
 	socklen_t addrlen;
+	int i;
 
 	addrlen = sizeof(struct sockaddr_in6);
 	ev.events = EPOLLIN;
@@ -308,24 +377,30 @@ static void test(void)
 	      accept_fd, errno);
 	close(listen_fd);
 
-	/* Send some data from accept_fd to cli_fd */
-	err = send(accept_fd, DATA, DATA_LEN, 0);
-	CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d",
-	      err, errno);
-
-	/* Have some timeout in recv(cli_fd). Just in case. */
 	ev.data.fd = cli_fd;
 	err = epoll_ctl(epfd, EPOLL_CTL_ADD, cli_fd, &ev);
 	CHECK(err, "epoll_ctl(EPOLL_CTL_ADD, cli_fd)", "err:%d errno:%d",
 	      err, errno);
 
-	err = epoll_wait(epfd, &ev, 1, 1000);
-	CHECK(err != 1 || ev.data.fd != cli_fd,
-	      "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d",
-	      err, errno, ev.data.fd, cli_fd);
+	init_sk_storage(accept_fd, 2);
 
-	err = recv(cli_fd, NULL, 0, MSG_TRUNC);
-	CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno);
+	for (i = 0; i < 2; i++) {
+		/* Send some data from accept_fd to cli_fd */
+		err = send(accept_fd, DATA, DATA_LEN, 0);
+		CHECK(err != DATA_LEN, "send(accept_fd)", "err:%d errno:%d",
+		      err, errno);
+
+		/* Have some timeout in recv(cli_fd). Just in case. */
+		err = epoll_wait(epfd, &ev, 1, 1000);
+		CHECK(err != 1 || ev.data.fd != cli_fd,
+		      "epoll_wait(cli_fd)", "err:%d errno:%d ev.data.fd:%d cli_fd:%d",
+		      err, errno, ev.data.fd, cli_fd);
+
+		err = recv(cli_fd, NULL, 0, MSG_TRUNC);
+		CHECK(err, "recv(cli_fd)", "err:%d errno:%d", err, errno);
+	}
+
+	check_sk_pkt_out_cnt(accept_fd, cli_fd);
 
 	close(epfd);
 	close(accept_fd);
@@ -395,6 +470,14 @@ int main(int argc, char **argv)
 	CHECK(!map, "cannot find linum_map", "(null)");
 	linum_map_fd = bpf_map__fd(map);
 
+	map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt");
+	CHECK(!map, "cannot find sk_pkt_out_cnt", "(null)");
+	sk_pkt_out_cnt_fd = bpf_map__fd(map);
+
+	map = bpf_object__find_map_by_name(obj, "sk_pkt_out_cnt10");
+	CHECK(!map, "cannot find sk_pkt_out_cnt10", "(null)");
+	sk_pkt_out_cnt10_fd = bpf_map__fd(map);
+
 	test();
 
 	bpf_object__close(obj);
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index ed9e894afef3..ccd896b98cac 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -47,12 +47,13 @@
 #include "bpf_rlimit.h"
 #include "bpf_rand.h"
 #include "bpf_util.h"
+#include "test_btf.h"
 #include "../../../include/linux/filter.h"
 
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	17
+#define MAX_NR_MAPS	18
 #define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
@@ -85,6 +86,7 @@ struct bpf_test {
 	int fixup_map_array_ro[MAX_FIXUPS];
 	int fixup_map_array_wo[MAX_FIXUPS];
 	int fixup_map_array_small[MAX_FIXUPS];
+	int fixup_sk_storage_map[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval, retval_unpriv, insn_processed;
@@ -497,24 +499,6 @@ static int create_cgroup_storage(bool percpu)
 	return fd;
 }
 
-#define BTF_INFO_ENC(kind, kind_flag, vlen) \
-	((!!(kind_flag) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN))
-#define BTF_TYPE_ENC(name, info, size_or_type) \
-	(name), (info), (size_or_type)
-#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \
-	((encoding) << 24 | (bits_offset) << 16 | (nr_bits))
-#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \
-	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \
-	BTF_INT_ENC(encoding, bits_offset, bits)
-#define BTF_MEMBER_ENC(name, type, bits_offset) \
-	(name), (type), (bits_offset)
-
-struct btf_raw_data {
-	__u32 raw_types[64];
-	const char *str_sec;
-	__u32 str_sec_size;
-};
-
 /* struct bpf_spin_lock {
  *   int val;
  * };
@@ -589,6 +573,31 @@ static int create_map_spin_lock(void)
 	return fd;
 }
 
+static int create_sk_storage_map(void)
+{
+	struct bpf_create_map_attr attr = {
+		.name = "test_map",
+		.map_type = BPF_MAP_TYPE_SK_STORAGE,
+		.key_size = 4,
+		.value_size = 8,
+		.max_entries = 0,
+		.map_flags = BPF_F_NO_PREALLOC,
+		.btf_key_type_id = 1,
+		.btf_value_type_id = 3,
+	};
+	int fd, btf_fd;
+
+	btf_fd = load_btf();
+	if (btf_fd < 0)
+		return -1;
+	attr.btf_fd = btf_fd;
+	fd = bpf_create_map_xattr(&attr);
+	close(attr.btf_fd);
+	if (fd < 0)
+		printf("Failed to create sk_storage_map\n");
+	return fd;
+}
+
 static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
@@ -611,6 +620,7 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_map_array_ro = test->fixup_map_array_ro;
 	int *fixup_map_array_wo = test->fixup_map_array_wo;
 	int *fixup_map_array_small = test->fixup_map_array_small;
+	int *fixup_sk_storage_map = test->fixup_sk_storage_map;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -765,6 +775,13 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_array_small++;
 		} while (*fixup_map_array_small);
 	}
+	if (*fixup_sk_storage_map) {
+		map_fds[17] = create_sk_storage_map();
+		do {
+			prog[*fixup_sk_storage_map].imm = map_fds[17];
+			fixup_sk_storage_map++;
+		} while (*fixup_sk_storage_map);
+	}
 }
 
 static int set_admin(bool admin)
diff --git a/tools/testing/selftests/bpf/verifier/sock.c b/tools/testing/selftests/bpf/verifier/sock.c
index 416436231fab..b31cd2cf50d0 100644
--- a/tools/testing/selftests/bpf/verifier/sock.c
+++ b/tools/testing/selftests/bpf/verifier/sock.c
@@ -382,3 +382,119 @@
 	.result = REJECT,
 	.errstr = "reference has not been acquired before",
 },
+{
+	"sk_storage_get(map, skb->sk, NULL, 0): value == NULL",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_sk_storage_map = { 11 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"sk_storage_get(map, skb->sk, 1, 1): value == 1",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_4, 1),
+	BPF_MOV64_IMM(BPF_REG_3, 1),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_sk_storage_map = { 11 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "R3 type=inv expected=fp",
+},
+{
+	"sk_storage_get(map, skb->sk, &stack_value, 1): stack_value",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_4, 1),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_sk_storage_map = { 14 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"sk_storage_get(map, skb->sk, &stack_value, 1): partially init stack_value",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, offsetof(struct __sk_buff, sk)),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_EMIT_CALL(BPF_FUNC_sk_fullsock),
+	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_4, 1),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -8),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_storage_get),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_sk_storage_map = { 14 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "invalid indirect read from stack",
+},
+{
+	"bpf_map_lookup_elem(smap, &key)",
+	.insns = {
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -4, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_sk_storage_map = { 3 },
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = REJECT,
+	.errstr = "cannot pass map_type 24 into func bpf_map_lookup_elem",
+},