Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2022-11-02

We've added 70 non-merge commits during the last 14 day(s) which contain
a total of 96 files changed, 3203 insertions(+), 640 deletions(-).

The main changes are:

1) Make cgroup local storage available to non-cgroup attached BPF programs
   such as tc BPF ones, from Yonghong Song.

2) Avoid unnecessary deadlock detection and failures wrt BPF task storage
   helpers, from Martin KaFai Lau.

3) Add LLVM disassembler as default library for dumping JITed code
   in bpftool, from Quentin Monnet.

4) Various kprobe_multi_link fixes related to kernel modules,
   from Jiri Olsa.

5) Optimize x86-64 JIT with emitting BMI2-based shift instructions,
   from Jie Meng.

6) Improve BPF verifier's memory type compatibility for map key/value
   arguments, from Dave Marchevsky.

7) Only create mmap-able data section maps in libbpf when data is exposed
   via skeletons, from Andrii Nakryiko.

8) Add an autoattach option for bpftool to load all object assets,
   from Wang Yufen.

9) Various memory handling fixes for libbpf and BPF selftests,
   from Xu Kuohai.

10) Initial support for BPF selftest's vmtest.sh on arm64,
    from Manu Bretelle.

11) Improve libbpf's BTF handling to dedup identical structs,
    from Alan Maguire.

12) Add BPF CI and denylist documentation for BPF selftests,
    from Daniel Müller.

13) Check BPF cpumap max_entries before doing allocation work,
    from Florian Lehner.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (70 commits)
  samples/bpf: Fix typo in README
  bpf: Remove the obsolte u64_stats_fetch_*_irq() users.
  bpf: check max_entries before allocating memory
  bpf: Fix a typo in comment for DFS algorithm
  bpftool: Fix spelling mistake "disasembler" -> "disassembler"
  selftests/bpf: Fix bpftool synctypes checking failure
  selftests/bpf: Panic on hard/soft lockup
  docs/bpf: Add documentation for new cgroup local storage
  selftests/bpf: Add test cgrp_local_storage to DENYLIST.s390x
  selftests/bpf: Add selftests for new cgroup local storage
  selftests/bpf: Fix test test_libbpf_str/bpf_map_type_str
  bpftool: Support new cgroup local storage
  libbpf: Support new cgroup local storage
  bpf: Implement cgroup storage available to non-cgroup-attached bpf progs
  bpf: Refactor some inode/task/sk storage functions for reuse
  bpf: Make struct cgroup btf id global
  selftests/bpf: Tracing prog can still do lookup under busy lock
  selftests/bpf: Ensure no task storage failure for bpf_lsm.s prog due to deadlock detection
  bpf: Add new bpf_task_storage_delete proto with no deadlock detection
  bpf: bpf_task_storage_delete_recur does lookup first before the deadlock check
  ...
====================

Link: https://lore.kernel.org/r/20221102062120.5724-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

8 files changed, 523 insertions, 13 deletions

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index c39d40f4b268..6f8ed61fc4b4 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -941,10 +941,10 @@ 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;
+	__u32 key, expected_key = 0, res_first_key;
+	int err, i, map_fd, hash_fd, iter_fd;
 	struct bpf_iter_bpf_array_map *skel;
 	union bpf_iter_link_info linfo;
-	int err, i, map_fd, iter_fd;
 	struct bpf_link *link;
 	char buf[64] = {};
 	int len, start;
@@ -1001,12 +1001,20 @@ static void test_bpf_array_map(void)
 	if (!ASSERT_EQ(skel->bss->val_sum, expected_val, "val_sum"))
 		goto close_iter;
 
+	hash_fd = bpf_map__fd(skel->maps.hashmap1);
 	for (i = 0; i < bpf_map__max_entries(skel->maps.arraymap1); i++) {
 		err = bpf_map_lookup_elem(map_fd, &i, &val);
-		if (!ASSERT_OK(err, "map_lookup"))
-			goto out;
-		if (!ASSERT_EQ(i, val, "invalid_val"))
-			goto out;
+		if (!ASSERT_OK(err, "map_lookup arraymap1"))
+			goto close_iter;
+		if (!ASSERT_EQ(i, val, "invalid_val arraymap1"))
+			goto close_iter;
+
+		val = i + 4;
+		err = bpf_map_lookup_elem(hash_fd, &val, &key);
+		if (!ASSERT_OK(err, "map_lookup hashmap1"))
+			goto close_iter;
+		if (!ASSERT_EQ(key, val - 4, "invalid_val hashmap1"))
+			goto close_iter;
 	}
 
 close_iter:
diff --git a/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
new file mode 100644
index 000000000000..1c30412ba132
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/cgrp_local_storage.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates.*/
+
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <test_progs.h>
+#include "cgrp_ls_tp_btf.skel.h"
+#include "cgrp_ls_recursion.skel.h"
+#include "cgrp_ls_attach_cgroup.skel.h"
+#include "cgrp_ls_negative.skel.h"
+#include "network_helpers.h"
+
+struct socket_cookie {
+	__u64 cookie_key;
+	__u32 cookie_value;
+};
+
+static void test_tp_btf(int cgroup_fd)
+{
+	struct cgrp_ls_tp_btf *skel;
+	long val1 = 1, val2 = 0;
+	int err;
+
+	skel = cgrp_ls_tp_btf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	/* populate a value in map_b */
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val1, BPF_ANY);
+	if (!ASSERT_OK(err, "map_update_elem"))
+		goto out;
+
+	/* check value */
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd, &val2);
+	if (!ASSERT_OK(err, "map_lookup_elem"))
+		goto out;
+	if (!ASSERT_EQ(val2, 1, "map_lookup_elem, invalid val"))
+		goto out;
+
+	/* delete value */
+	err = bpf_map_delete_elem(bpf_map__fd(skel->maps.map_b), &cgroup_fd);
+	if (!ASSERT_OK(err, "map_delete_elem"))
+		goto out;
+
+	skel->bss->target_pid = syscall(SYS_gettid);
+
+	err = cgrp_ls_tp_btf__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	syscall(SYS_gettid);
+	syscall(SYS_gettid);
+
+	skel->bss->target_pid = 0;
+
+	/* 3x syscalls: 1x attach and 2x gettid */
+	ASSERT_EQ(skel->bss->enter_cnt, 3, "enter_cnt");
+	ASSERT_EQ(skel->bss->exit_cnt, 3, "exit_cnt");
+	ASSERT_EQ(skel->bss->mismatch_cnt, 0, "mismatch_cnt");
+out:
+	cgrp_ls_tp_btf__destroy(skel);
+}
+
+static void test_attach_cgroup(int cgroup_fd)
+{
+	int server_fd = 0, client_fd = 0, err = 0;
+	socklen_t addr_len = sizeof(struct sockaddr_in6);
+	struct cgrp_ls_attach_cgroup *skel;
+	__u32 cookie_expected_value;
+	struct sockaddr_in6 addr;
+	struct socket_cookie val;
+
+	skel = cgrp_ls_attach_cgroup__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	skel->links.set_cookie = bpf_program__attach_cgroup(
+		skel->progs.set_cookie, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.set_cookie, "prog_attach"))
+		goto out;
+
+	skel->links.update_cookie_sockops = bpf_program__attach_cgroup(
+		skel->progs.update_cookie_sockops, cgroup_fd);
+	if (!ASSERT_OK_PTR(skel->links.update_cookie_sockops, "prog_attach"))
+		goto out;
+
+	skel->links.update_cookie_tracing = bpf_program__attach(
+		skel->progs.update_cookie_tracing);
+	if (!ASSERT_OK_PTR(skel->links.update_cookie_tracing, "prog_attach"))
+		goto out;
+
+	server_fd = start_server(AF_INET6, SOCK_STREAM, "::1", 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_server"))
+		goto out;
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect_to_fd"))
+		goto close_server_fd;
+
+	err = bpf_map_lookup_elem(bpf_map__fd(skel->maps.socket_cookies),
+				  &cgroup_fd, &val);
+	if (!ASSERT_OK(err, "map_lookup(socket_cookies)"))
+		goto close_client_fd;
+
+	err = getsockname(client_fd, (struct sockaddr *)&addr, &addr_len);
+	if (!ASSERT_OK(err, "getsockname"))
+		goto close_client_fd;
+
+	cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF;
+	ASSERT_EQ(val.cookie_value, cookie_expected_value, "cookie_value");
+
+close_client_fd:
+	close(client_fd);
+close_server_fd:
+	close(server_fd);
+out:
+	cgrp_ls_attach_cgroup__destroy(skel);
+}
+
+static void test_recursion(int cgroup_fd)
+{
+	struct cgrp_ls_recursion *skel;
+	int err;
+
+	skel = cgrp_ls_recursion__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
+		return;
+
+	err = cgrp_ls_recursion__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto out;
+
+	/* trigger sys_enter, make sure it does not cause deadlock */
+	syscall(SYS_gettid);
+
+out:
+	cgrp_ls_recursion__destroy(skel);
+}
+
+static void test_negative(void)
+{
+	struct cgrp_ls_negative *skel;
+
+	skel = cgrp_ls_negative__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "skel_open_and_load")) {
+		cgrp_ls_negative__destroy(skel);
+		return;
+	}
+}
+
+void test_cgrp_local_storage(void)
+{
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/cgrp_local_storage");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /cgrp_local_storage"))
+		return;
+
+	if (test__start_subtest("tp_btf"))
+		test_tp_btf(cgroup_fd);
+	if (test__start_subtest("attach_cgroup"))
+		test_attach_cgroup(cgroup_fd);
+	if (test__start_subtest("recursion"))
+		test_recursion(cgroup_fd);
+	if (test__start_subtest("negative"))
+		test_negative();
+
+	close(cgroup_fd);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
new file mode 100644
index 000000000000..1fbe7e4ac00a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/kprobe_multi_testmod_test.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include "kprobe_multi.skel.h"
+#include "trace_helpers.h"
+#include "bpf/libbpf_internal.h"
+
+static void kprobe_multi_testmod_check(struct kprobe_multi *skel)
+{
+	ASSERT_EQ(skel->bss->kprobe_testmod_test1_result, 1, "kprobe_test1_result");
+	ASSERT_EQ(skel->bss->kprobe_testmod_test2_result, 1, "kprobe_test2_result");
+	ASSERT_EQ(skel->bss->kprobe_testmod_test3_result, 1, "kprobe_test3_result");
+
+	ASSERT_EQ(skel->bss->kretprobe_testmod_test1_result, 1, "kretprobe_test1_result");
+	ASSERT_EQ(skel->bss->kretprobe_testmod_test2_result, 1, "kretprobe_test2_result");
+	ASSERT_EQ(skel->bss->kretprobe_testmod_test3_result, 1, "kretprobe_test3_result");
+}
+
+static void test_testmod_attach_api(struct bpf_kprobe_multi_opts *opts)
+{
+	struct kprobe_multi *skel = NULL;
+
+	skel = kprobe_multi__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "fentry_raw_skel_load"))
+		return;
+
+	skel->bss->pid = getpid();
+
+	skel->links.test_kprobe_testmod = bpf_program__attach_kprobe_multi_opts(
+						skel->progs.test_kprobe_testmod,
+						NULL, opts);
+	if (!skel->links.test_kprobe_testmod)
+		goto cleanup;
+
+	opts->retprobe = true;
+	skel->links.test_kretprobe_testmod = bpf_program__attach_kprobe_multi_opts(
+						skel->progs.test_kretprobe_testmod,
+						NULL, opts);
+	if (!skel->links.test_kretprobe_testmod)
+		goto cleanup;
+
+	ASSERT_OK(trigger_module_test_read(1), "trigger_read");
+	kprobe_multi_testmod_check(skel);
+
+cleanup:
+	kprobe_multi__destroy(skel);
+}
+
+static void test_testmod_attach_api_addrs(void)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	unsigned long long addrs[3];
+
+	addrs[0] = ksym_get_addr("bpf_testmod_fentry_test1");
+	ASSERT_NEQ(addrs[0], 0, "ksym_get_addr");
+	addrs[1] = ksym_get_addr("bpf_testmod_fentry_test2");
+	ASSERT_NEQ(addrs[1], 0, "ksym_get_addr");
+	addrs[2] = ksym_get_addr("bpf_testmod_fentry_test3");
+	ASSERT_NEQ(addrs[2], 0, "ksym_get_addr");
+
+	opts.addrs = (const unsigned long *) addrs;
+	opts.cnt = ARRAY_SIZE(addrs);
+
+	test_testmod_attach_api(&opts);
+}
+
+static void test_testmod_attach_api_syms(void)
+{
+	LIBBPF_OPTS(bpf_kprobe_multi_opts, opts);
+	const char *syms[3] = {
+		"bpf_testmod_fentry_test1",
+		"bpf_testmod_fentry_test2",
+		"bpf_testmod_fentry_test3",
+	};
+
+	opts.syms = syms;
+	opts.cnt = ARRAY_SIZE(syms);
+	test_testmod_attach_api(&opts);
+}
+
+void serial_test_kprobe_multi_testmod_test(void)
+{
+	if (!ASSERT_OK(load_kallsyms_refresh(), "load_kallsyms_refresh"))
+		return;
+
+	if (test__start_subtest("testmod_attach_api_syms"))
+		test_testmod_attach_api_syms();
+	if (test__start_subtest("testmod_attach_api_addrs"))
+		test_testmod_attach_api_addrs();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
index 93e9cddaadcf..efb8bd43653c 100644
--- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
+++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c
@@ -139,6 +139,14 @@ static void test_libbpf_bpf_map_type_str(void)
 		snprintf(buf, sizeof(buf), "BPF_MAP_TYPE_%s", map_type_str);
 		uppercase(buf);
 
+		/* Special case for map_type_name BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED
+		 * where it and BPF_MAP_TYPE_CGROUP_STORAGE have the same enum value
+		 * (map_type). For this enum value, libbpf_bpf_map_type_str() picks
+		 * BPF_MAP_TYPE_CGROUP_STORAGE.
+		 */
+		if (strcmp(map_type_name, "BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED") == 0)
+			continue;
+
 		ASSERT_STREQ(buf, map_type_name, "exp_str_value");
 	}
 
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 6d0e50dcf47c..7fc01ff490db 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -103,6 +103,13 @@ void test_module_attach(void)
 	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
 	bpf_link__destroy(link);
 
+	link = bpf_program__attach(skel->progs.kprobe_multi);
+	if (!ASSERT_OK_PTR(link, "attach_kprobe_multi"))
+		goto cleanup;
+
+	ASSERT_ERR(delete_module("bpf_testmod", 0), "delete_module");
+	bpf_link__destroy(link);
+
 cleanup:
 	test_module_attach__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 9a80fe8a6427..ac104dc652e3 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -13,6 +13,7 @@
 #include <linux/perf_event.h>
 #include <linux/ring_buffer.h>
 #include "test_ringbuf.lskel.h"
+#include "test_ringbuf_map_key.lskel.h"
 
 #define EDONE 7777
 
@@ -58,6 +59,7 @@ static int process_sample(void *ctx, void *data, size_t len)
 	}
 }
 
+static struct test_ringbuf_map_key_lskel *skel_map_key;
 static struct test_ringbuf_lskel *skel;
 static struct ring_buffer *ringbuf;
 
@@ -81,7 +83,7 @@ static void *poll_thread(void *input)
 	return (void *)(long)ring_buffer__poll(ringbuf, timeout);
 }
 
-void test_ringbuf(void)
+static void ringbuf_subtest(void)
 {
 	const size_t rec_sz = BPF_RINGBUF_HDR_SZ + sizeof(struct sample);
 	pthread_t thread;
@@ -297,3 +299,65 @@ cleanup:
 	ring_buffer__free(ringbuf);
 	test_ringbuf_lskel__destroy(skel);
 }
+
+static int process_map_key_sample(void *ctx, void *data, size_t len)
+{
+	struct sample *s;
+	int err, val;
+
+	s = data;
+	switch (s->seq) {
+	case 1:
+		ASSERT_EQ(s->value, 42, "sample_value");
+		err = bpf_map_lookup_elem(skel_map_key->maps.hash_map.map_fd,
+					  s, &val);
+		ASSERT_OK(err, "hash_map bpf_map_lookup_elem");
+		ASSERT_EQ(val, 1, "hash_map val");
+		return -EDONE;
+	default:
+		return 0;
+	}
+}
+
+static void ringbuf_map_key_subtest(void)
+{
+	int err;
+
+	skel_map_key = test_ringbuf_map_key_lskel__open();
+	if (!ASSERT_OK_PTR(skel_map_key, "test_ringbuf_map_key_lskel__open"))
+		return;
+
+	skel_map_key->maps.ringbuf.max_entries = getpagesize();
+	skel_map_key->bss->pid = getpid();
+
+	err = test_ringbuf_map_key_lskel__load(skel_map_key);
+	if (!ASSERT_OK(err, "test_ringbuf_map_key_lskel__load"))
+		goto cleanup;
+
+	ringbuf = ring_buffer__new(skel_map_key->maps.ringbuf.map_fd,
+				   process_map_key_sample, NULL, NULL);
+	if (!ASSERT_OK_PTR(ringbuf, "ring_buffer__new"))
+		goto cleanup;
+
+	err = test_ringbuf_map_key_lskel__attach(skel_map_key);
+	if (!ASSERT_OK(err, "test_ringbuf_map_key_lskel__attach"))
+		goto cleanup_ringbuf;
+
+	syscall(__NR_getpgid);
+	ASSERT_EQ(skel_map_key->bss->seq, 1, "skel_map_key->bss->seq");
+	err = ring_buffer__poll(ringbuf, -1);
+	ASSERT_EQ(err, -EDONE, "ring_buffer__poll");
+
+cleanup_ringbuf:
+	ring_buffer__free(ringbuf);
+cleanup:
+	test_ringbuf_map_key_lskel__destroy(skel_map_key);
+}
+
+void test_ringbuf(void)
+{
+	if (test__start_subtest("ringbuf"))
+		ringbuf_subtest();
+	if (test__start_subtest("ringbuf_map_key"))
+		ringbuf_map_key_subtest();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index 99dac5292b41..bc6817aee9aa 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019 Facebook */
 
 #include <test_progs.h>
+#include <sys/mman.h>
 
 struct s {
 	int a;
@@ -22,7 +23,8 @@ void test_skeleton(void)
 	struct test_skeleton__kconfig *kcfg;
 	const void *elf_bytes;
 	size_t elf_bytes_sz = 0;
-	int i;
+	void *m;
+	int i, fd;
 
 	skel = test_skeleton__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -124,6 +126,13 @@ void test_skeleton(void)
 
 	ASSERT_EQ(bss->huge_arr[ARRAY_SIZE(bss->huge_arr) - 1], 123, "huge_arr");
 
+	fd = bpf_map__fd(skel->maps.data_non_mmapable);
+	m = mmap(NULL, getpagesize(), PROT_READ, MAP_SHARED, fd, 0);
+	if (!ASSERT_EQ(m, MAP_FAILED, "unexpected_mmap_success"))
+		munmap(m, getpagesize());
+
+	ASSERT_EQ(bpf_map__map_flags(skel->maps.data_non_mmapable), 0, "non_mmap_flags");
+
 	elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz);
 	ASSERT_OK_PTR(elf_bytes, "elf_bytes");
 	ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz");
diff --git a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
index 035c263aab1b..a176bd75a748 100644
--- a/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
+++ b/tools/testing/selftests/bpf/prog_tests/task_local_storage.c
@@ -3,12 +3,16 @@
 
 #define _GNU_SOURCE         /* See feature_test_macros(7) */
 #include <unistd.h>
+#include <sched.h>
+#include <pthread.h>
 #include <sys/syscall.h>   /* For SYS_xxx definitions */
 #include <sys/types.h>
 #include <test_progs.h>
+#include "task_local_storage_helpers.h"
 #include "task_local_storage.skel.h"
 #include "task_local_storage_exit_creds.skel.h"
 #include "task_ls_recursion.skel.h"
+#include "task_storage_nodeadlock.skel.h"
 
 static void test_sys_enter_exit(void)
 {
@@ -39,7 +43,8 @@ out:
 static void test_exit_creds(void)
 {
 	struct task_local_storage_exit_creds *skel;
-	int err;
+	int err, run_count, sync_rcu_calls = 0;
+	const int MAX_SYNC_RCU_CALLS = 1000;
 
 	skel = task_local_storage_exit_creds__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
@@ -53,8 +58,19 @@ static void test_exit_creds(void)
 	if (CHECK_FAIL(system("ls > /dev/null")))
 		goto out;
 
-	/* sync rcu to make sure exit_creds() is called for "ls" */
-	kern_sync_rcu();
+	/* kern_sync_rcu is not enough on its own as the read section we want
+	 * to wait for may start after we enter synchronize_rcu, so our call
+	 * won't wait for the section to finish. Loop on the run counter
+	 * as well to ensure the program has run.
+	 */
+	do {
+		kern_sync_rcu();
+		run_count = __atomic_load_n(&skel->bss->run_count, __ATOMIC_SEQ_CST);
+	} while (run_count == 0 && ++sync_rcu_calls < MAX_SYNC_RCU_CALLS);
+
+	ASSERT_NEQ(sync_rcu_calls, MAX_SYNC_RCU_CALLS,
+		   "sync_rcu count too high");
+	ASSERT_NEQ(run_count, 0, "run_count");
 	ASSERT_EQ(skel->bss->valid_ptr_count, 0, "valid_ptr_count");
 	ASSERT_NEQ(skel->bss->null_ptr_count, 0, "null_ptr_count");
 out:
@@ -63,24 +79,160 @@ out:
 
 static void test_recursion(void)
 {
+	int err, map_fd, prog_fd, task_fd;
 	struct task_ls_recursion *skel;
-	int err;
+	struct bpf_prog_info info;
+	__u32 info_len = sizeof(info);
+	long value;
+
+	task_fd = sys_pidfd_open(getpid(), 0);
+	if (!ASSERT_NEQ(task_fd, -1, "sys_pidfd_open"))
+		return;
 
 	skel = task_ls_recursion__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel_open_and_load"))
-		return;
+		goto out;
 
 	err = task_ls_recursion__attach(skel);
 	if (!ASSERT_OK(err, "skel_attach"))
 		goto out;
 
 	/* trigger sys_enter, make sure it does not cause deadlock */
+	skel->bss->test_pid = getpid();
 	syscall(SYS_gettid);
+	skel->bss->test_pid = 0;
+	task_ls_recursion__detach(skel);
+
+	/* Refer to the comment in BPF_PROG(on_update) for
+	 * the explanation on the value 201 and 100.
+	 */
+	map_fd = bpf_map__fd(skel->maps.map_a);
+	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
+	ASSERT_OK(err, "lookup map_a");
+	ASSERT_EQ(value, 201, "map_a value");
+	ASSERT_EQ(skel->bss->nr_del_errs, 1, "bpf_task_storage_delete busy");
+
+	map_fd = bpf_map__fd(skel->maps.map_b);
+	err = bpf_map_lookup_elem(map_fd, &task_fd, &value);
+	ASSERT_OK(err, "lookup map_b");
+	ASSERT_EQ(value, 100, "map_b value");
+
+	prog_fd = bpf_program__fd(skel->progs.on_lookup);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_GT(info.recursion_misses, 0, "on_lookup prog recursion");
+
+	prog_fd = bpf_program__fd(skel->progs.on_update);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_EQ(info.recursion_misses, 0, "on_update prog recursion");
+
+	prog_fd = bpf_program__fd(skel->progs.on_enter);
+	memset(&info, 0, sizeof(info));
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_EQ(info.recursion_misses, 0, "on_enter prog recursion");
 
 out:
+	close(task_fd);
 	task_ls_recursion__destroy(skel);
 }
 
+static bool stop;
+
+static void waitall(const pthread_t *tids, int nr)
+{
+	int i;
+
+	stop = true;
+	for (i = 0; i < nr; i++)
+		pthread_join(tids[i], NULL);
+}
+
+static void *sock_create_loop(void *arg)
+{
+	struct task_storage_nodeadlock *skel = arg;
+	int fd;
+
+	while (!stop) {
+		fd = socket(AF_INET, SOCK_STREAM, 0);
+		close(fd);
+		if (skel->bss->nr_get_errs || skel->bss->nr_del_errs)
+			stop = true;
+	}
+
+	return NULL;
+}
+
+static void test_nodeadlock(void)
+{
+	struct task_storage_nodeadlock *skel;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	const int nr_threads = 32;
+	pthread_t tids[nr_threads];
+	int i, prog_fd, err;
+	cpu_set_t old, new;
+
+	/* Pin all threads to one cpu to increase the chance of preemption
+	 * in a sleepable bpf prog.
+	 */
+	CPU_ZERO(&new);
+	CPU_SET(0, &new);
+	err = sched_getaffinity(getpid(), sizeof(old), &old);
+	if (!ASSERT_OK(err, "getaffinity"))
+		return;
+	err = sched_setaffinity(getpid(), sizeof(new), &new);
+	if (!ASSERT_OK(err, "setaffinity"))
+		return;
+
+	skel = task_storage_nodeadlock__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open_and_load"))
+		goto done;
+
+	/* Unnecessary recursion and deadlock detection are reproducible
+	 * in the preemptible kernel.
+	 */
+	if (!skel->kconfig->CONFIG_PREEMPT) {
+		test__skip();
+		goto done;
+	}
+
+	err = task_storage_nodeadlock__attach(skel);
+	ASSERT_OK(err, "attach prog");
+
+	for (i = 0; i < nr_threads; i++) {
+		err = pthread_create(&tids[i], NULL, sock_create_loop, skel);
+		if (err) {
+			/* Only assert once here to avoid excessive
+			 * PASS printing during test failure.
+			 */
+			ASSERT_OK(err, "pthread_create");
+			waitall(tids, i);
+			goto done;
+		}
+	}
+
+	/* With 32 threads, 1s is enough to reproduce the issue */
+	sleep(1);
+	waitall(tids, nr_threads);
+
+	info_len = sizeof(info);
+	prog_fd = bpf_program__fd(skel->progs.socket_post_create);
+	err = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len);
+	ASSERT_OK(err, "get prog info");
+	ASSERT_EQ(info.recursion_misses, 0, "prog recursion");
+
+	ASSERT_EQ(skel->bss->nr_get_errs, 0, "bpf_task_storage_get busy");
+	ASSERT_EQ(skel->bss->nr_del_errs, 0, "bpf_task_storage_delete busy");
+
+done:
+	task_storage_nodeadlock__destroy(skel);
+	sched_setaffinity(getpid(), sizeof(old), &old);
+}
+
 void test_task_local_storage(void)
 {
 	if (test__start_subtest("sys_enter_exit"))
@@ -89,4 +241,6 @@ void test_task_local_storage(void)
 		test_exit_creds();
 	if (test__start_subtest("recursion"))
 		test_recursion();
+	if (test__start_subtest("nodeadlock"))
+		test_nodeadlock();
 }