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

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-04-09

We've added 63 non-merge commits during the last 9 day(s) which contain
a total of 68 files changed, 4852 insertions(+), 619 deletions(-).

The main changes are:

1) Add libbpf support for USDT (User Statically-Defined Tracing) probes.
   USDTs are an abstraction built on top of uprobes, critical for tracing
   and BPF, and widely used in production applications, from Andrii Nakryiko.

2) While Andrii was adding support for x86{-64}-specific logic of parsing
   USDT argument specification, Ilya followed-up with USDT support for s390
   architecture, from Ilya Leoshkevich.

3) Support name-based attaching for uprobe BPF programs in libbpf. The format
   supported is `u[ret]probe/binary_path:[raw_offset|function[+offset]]`, e.g.
   attaching to libc malloc can be done in BPF via SEC("uprobe/libc.so.6:malloc")
   now, from Alan Maguire.

4) Various load/store optimizations for the arm64 JIT to shrink the image
   size by using arm64 str/ldr immediate instructions. Also enable pointer
   authentication to verify return address for JITed code, from Xu Kuohai.

5) BPF verifier fixes for write access checks to helper functions, e.g.
   rd-only memory from bpf_*_cpu_ptr() must not be passed to helpers that
   write into passed buffers, from Kumar Kartikeya Dwivedi.

6) Fix overly excessive stack map allocation for its base map structure and
   buckets which slipped-in from cleanups during the rlimit accounting removal
   back then, from Yuntao Wang.

7) Extend the unstable CT lookup helpers for XDP and tc/BPF to report netfilter
   connection tracking tuple direction, from Lorenzo Bianconi.

8) Improve bpftool dump to show BPF program/link type names, Milan Landaverde.

9) Minor cleanups all over the place from various others.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (63 commits)
  bpf: Fix excessive memory allocation in stack_map_alloc()
  selftests/bpf: Fix return value checks in perf_event_stackmap test
  selftests/bpf: Add CO-RE relos into linked_funcs selftests
  libbpf: Use weak hidden modifier for USDT BPF-side API functions
  libbpf: Don't error out on CO-RE relos for overriden weak subprogs
  samples, bpf: Move routes monitor in xdp_router_ipv4 in a dedicated thread
  libbpf: Allow WEAK and GLOBAL bindings during BTF fixup
  libbpf: Use strlcpy() in path resolution fallback logic
  libbpf: Add s390-specific USDT arg spec parsing logic
  libbpf: Make BPF-side of USDT support work on big-endian machines
  libbpf: Minor style improvements in USDT code
  libbpf: Fix use #ifdef instead of #if to avoid compiler warning
  libbpf: Potential NULL dereference in usdt_manager_attach_usdt()
  selftests/bpf: Uprobe tests should verify param/return values
  libbpf: Improve string parsing for uprobe auto-attach
  libbpf: Improve library identification for uprobe binary path resolution
  selftests/bpf: Test for writes to map key from BPF helpers
  selftests/bpf: Test passing rdonly mem to global func
  bpf: Reject writes for PTR_TO_MAP_KEY in check_helper_mem_access
  bpf: Check PTR_TO_MEM | MEM_RDONLY in check_helper_mem_access
  ...
====================

Link: https://lore.kernel.org/r/20220408231741.19116-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

39 files changed, 1609 insertions, 65 deletions

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 3820608faf57..bafdc5373a13 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -168,9 +168,15 @@ $(OUTPUT)/%:%.c
 	$(call msg,BINARY,,$@)
 	$(Q)$(LINK.c) $^ $(LDLIBS) -o $@
 
-$(OUTPUT)/urandom_read: urandom_read.c
+$(OUTPUT)/liburandom_read.so: urandom_read_lib1.c urandom_read_lib2.c
+	$(call msg,LIB,,$@)
+	$(Q)$(CC) $(CFLAGS) -fPIC $(LDFLAGS) $^ $(LDLIBS) --shared -o $@
+
+$(OUTPUT)/urandom_read: urandom_read.c urandom_read_aux.c $(OUTPUT)/liburandom_read.so
 	$(call msg,BINARY,,$@)
-	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $< $(LDLIBS) -Wl,--build-id=sha1 -o $@
+	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.c,$^)			       \
+		  liburandom_read.so $(LDLIBS)	       			       \
+		  -Wl,-rpath=. -Wl,--build-id=sha1 -o $@
 
 $(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch])
 	$(call msg,MOD,,$@)
@@ -328,12 +334,8 @@ SKEL_BLACKLIST := btf__% test_pinning_invalid.c test_sk_assign.c
 
 LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		linked_vars.skel.h linked_maps.skel.h 			\
-		test_subskeleton.skel.h test_subskeleton_lib.skel.h
-
-# In the subskeleton case, we want the test_subskeleton_lib.subskel.h file
-# but that's created as a side-effect of the skel.h generation.
-test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o
-test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o
+		test_subskeleton.skel.h test_subskeleton_lib.skel.h	\
+		test_usdt.skel.h
 
 LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
 	test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c \
@@ -346,6 +348,11 @@ test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
 linked_funcs.skel.h-deps := linked_funcs1.o linked_funcs2.o
 linked_vars.skel.h-deps := linked_vars1.o linked_vars2.o
 linked_maps.skel.h-deps := linked_maps1.o linked_maps2.o
+# In the subskeleton case, we want the test_subskeleton_lib.subskel.h file
+# but that's created as a side-effect of the skel.h generation.
+test_subskeleton.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o test_subskeleton.o
+test_subskeleton_lib.skel.h-deps := test_subskeleton_lib2.o test_subskeleton_lib.o
+test_usdt.skel.h-deps := test_usdt.o test_usdt_multispec.o
 
 LINKED_BPF_SRCS := $(patsubst %.o,%.c,$(foreach skel,$(LINKED_SKELS),$($(skel)-deps)))
 
@@ -400,6 +407,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.o:				\
 		     $(TRUNNER_BPF_PROGS_DIR)/*.h			\
 		     $$(INCLUDE_DIR)/vmlinux.h				\
 		     $(wildcard $(BPFDIR)/bpf_*.h)			\
+		     $(wildcard $(BPFDIR)/*.bpf.h)			\
 		     | $(TRUNNER_OUTPUT) $$(BPFOBJ)
 	$$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@,			\
 					  $(TRUNNER_BPF_CFLAGS))
@@ -491,6 +499,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c	\
 			 btf_helpers.c flow_dissector_load.h		\
 			 cap_helpers.c
 TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko	\
+		       $(OUTPUT)/liburandom_read.so			\
 		       ima_setup.sh					\
 		       $(wildcard progs/btf_dump_test_case_*.c)
 TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE
diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index d48f6e533e1e..c0c6d410751d 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -11,15 +11,22 @@ static void trigger_func(void)
 	asm volatile ("");
 }
 
+/* attach point for byname uprobe */
+static void trigger_func2(void)
+{
+	asm volatile ("");
+}
+
 void test_attach_probe(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
-	int duration = 0;
 	struct bpf_link *kprobe_link, *kretprobe_link;
 	struct bpf_link *uprobe_link, *uretprobe_link;
 	struct test_attach_probe* skel;
 	ssize_t uprobe_offset, ref_ctr_offset;
+	struct bpf_link *uprobe_err_link;
 	bool legacy;
+	char *mem;
 
 	/* Check if new-style kprobe/uprobe API is supported.
 	 * Kernels that support new FD-based kprobe and uprobe BPF attachment
@@ -43,9 +50,9 @@ void test_attach_probe(void)
 		return;
 
 	skel = test_attach_probe__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
 		return;
-	if (CHECK(!skel->bss, "check_bss", ".bss wasn't mmap()-ed\n"))
+	if (!ASSERT_OK_PTR(skel->bss, "check_bss"))
 		goto cleanup;
 
 	kprobe_link = bpf_program__attach_kprobe(skel->progs.handle_kprobe,
@@ -90,25 +97,73 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_uretprobe = uretprobe_link;
 
-	/* trigger & validate kprobe && kretprobe */
-	usleep(1);
+	/* verify auto-attach fails for old-style uprobe definition */
+	uprobe_err_link = bpf_program__attach(skel->progs.handle_uprobe_byname);
+	if (!ASSERT_EQ(libbpf_get_error(uprobe_err_link), -EOPNOTSUPP,
+		       "auto-attach should fail for old-style name"))
+		goto cleanup;
+
+	uprobe_opts.func_name = "trigger_func2";
+	uprobe_opts.retprobe = false;
+	uprobe_opts.ref_ctr_offset = 0;
+	skel->links.handle_uprobe_byname =
+			bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname,
+							0 /* this pid */,
+							"/proc/self/exe",
+							0, &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname, "attach_uprobe_byname"))
+		goto cleanup;
+
+	/* verify auto-attach works */
+	skel->links.handle_uretprobe_byname =
+			bpf_program__attach(skel->progs.handle_uretprobe_byname);
+	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname, "attach_uretprobe_byname"))
+		goto cleanup;
 
-	if (CHECK(skel->bss->kprobe_res != 1, "check_kprobe_res",
-		  "wrong kprobe res: %d\n", skel->bss->kprobe_res))
+	/* test attach by name for a library function, using the library
+	 * as the binary argument. libc.so.6 will be resolved via dlopen()/dlinfo().
+	 */
+	uprobe_opts.func_name = "malloc";
+	uprobe_opts.retprobe = false;
+	skel->links.handle_uprobe_byname2 =
+			bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe_byname2,
+							0 /* this pid */,
+							"libc.so.6",
+							0, &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.handle_uprobe_byname2, "attach_uprobe_byname2"))
 		goto cleanup;
-	if (CHECK(skel->bss->kretprobe_res != 2, "check_kretprobe_res",
-		  "wrong kretprobe res: %d\n", skel->bss->kretprobe_res))
+
+	uprobe_opts.func_name = "free";
+	uprobe_opts.retprobe = true;
+	skel->links.handle_uretprobe_byname2 =
+			bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe_byname2,
+							-1 /* any pid */,
+							"libc.so.6",
+							0, &uprobe_opts);
+	if (!ASSERT_OK_PTR(skel->links.handle_uretprobe_byname2, "attach_uretprobe_byname2"))
 		goto cleanup;
 
+	/* trigger & validate kprobe && kretprobe */
+	usleep(1);
+
+	/* trigger & validate shared library u[ret]probes attached by name */
+	mem = malloc(1);
+	free(mem);
+
 	/* trigger & validate uprobe & uretprobe */
 	trigger_func();
 
-	if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res",
-		  "wrong uprobe res: %d\n", skel->bss->uprobe_res))
-		goto cleanup;
-	if (CHECK(skel->bss->uretprobe_res != 4, "check_uretprobe_res",
-		  "wrong uretprobe res: %d\n", skel->bss->uretprobe_res))
-		goto cleanup;
+	/* trigger & validate uprobe attached by name */
+	trigger_func2();
+
+	ASSERT_EQ(skel->bss->kprobe_res, 1, "check_kprobe_res");
+	ASSERT_EQ(skel->bss->kretprobe_res, 2, "check_kretprobe_res");
+	ASSERT_EQ(skel->bss->uprobe_res, 3, "check_uprobe_res");
+	ASSERT_EQ(skel->bss->uretprobe_res, 4, "check_uretprobe_res");
+	ASSERT_EQ(skel->bss->uprobe_byname_res, 5, "check_uprobe_byname_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname_res, 6, "check_uretprobe_byname_res");
+	ASSERT_EQ(skel->bss->uprobe_byname2_res, 7, "check_uprobe_byname2_res");
+	ASSERT_EQ(skel->bss->uretprobe_byname2_res, 8, "check_uretprobe_byname2_res");
 
 cleanup:
 	test_attach_probe__destroy(skel);
diff --git a/tools/testing/selftests/bpf/prog_tests/for_each.c b/tools/testing/selftests/bpf/prog_tests/for_each.c
index 044df13ee069..754e80937e5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/for_each.c
+++ b/tools/testing/selftests/bpf/prog_tests/for_each.c
@@ -4,6 +4,7 @@
 #include <network_helpers.h>
 #include "for_each_hash_map_elem.skel.h"
 #include "for_each_array_map_elem.skel.h"
+#include "for_each_map_elem_write_key.skel.h"
 
 static unsigned int duration;
 
@@ -129,10 +130,21 @@ out:
 	for_each_array_map_elem__destroy(skel);
 }
 
+static void test_write_map_key(void)
+{
+	struct for_each_map_elem_write_key *skel;
+
+	skel = for_each_map_elem_write_key__open_and_load();
+	if (!ASSERT_ERR_PTR(skel, "for_each_map_elem_write_key__open_and_load"))
+		for_each_map_elem_write_key__destroy(skel);
+}
+
 void test_for_each(void)
 {
 	if (test__start_subtest("hash_map"))
 		test_hash_map();
 	if (test__start_subtest("array_map"))
 		test_array_map();
+	if (test__start_subtest("write_map_key"))
+		test_write_map_key();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index f6933b06daf8..1d7a2f1e0731 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -138,12 +138,16 @@ cleanup:
 	test_ksyms_weak_lskel__destroy(skel);
 }
 
-static void test_write_check(void)
+static void test_write_check(bool test_handler1)
 {
 	struct test_ksyms_btf_write_check *skel;
 
-	skel = test_ksyms_btf_write_check__open_and_load();
-	ASSERT_ERR_PTR(skel, "unexpected load of a prog writing to ksym memory\n");
+	skel = test_ksyms_btf_write_check__open();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_btf_write_check__open"))
+		return;
+	bpf_program__set_autoload(test_handler1 ? skel->progs.handler2 : skel->progs.handler1, false);
+	ASSERT_ERR(test_ksyms_btf_write_check__load(skel),
+		   "unexpected load of a prog writing to ksym memory\n");
 
 	test_ksyms_btf_write_check__destroy(skel);
 }
@@ -179,6 +183,9 @@ void test_ksyms_btf(void)
 	if (test__start_subtest("weak_ksyms_lskel"))
 		test_weak_syms_lskel();
 
-	if (test__start_subtest("write_check"))
-		test_write_check();
+	if (test__start_subtest("write_check1"))
+		test_write_check(true);
+
+	if (test__start_subtest("write_check2"))
+		test_write_check(false);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c
index 954964f0ac3d..d3915c58d0e1 100644
--- a/tools/testing/selftests/bpf/prog_tests/netcnt.c
+++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c
@@ -25,7 +25,7 @@ void serial_test_netcnt(void)
 	if (!ASSERT_OK_PTR(skel, "netcnt_prog__open_and_load"))
 		return;
 
-	nproc = get_nprocs_conf();
+	nproc = bpf_num_possible_cpus();
 	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
 	if (!ASSERT_OK_PTR(percpu_netcnt, "malloc(percpu_netcnt)"))
 		goto err;
diff --git a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
index 509e21d5cb9d..b90ee47d3111 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_global_funcs.c
@@ -81,6 +81,7 @@ void test_test_global_funcs(void)
 		{ "test_global_func14.o", "reference type('FWD S') size cannot be determined" },
 		{ "test_global_func15.o", "At program exit the register R0 has value" },
 		{ "test_global_func16.o", "invalid indirect read from stack" },
+		{ "test_global_func17.o", "Caller passes invalid args into func#1" },
 	};
 	libbpf_print_fn_t old_print_fn = NULL;
 	int err, i, duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
new file mode 100644
index 000000000000..d6003dc8cc99
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_autoattach.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Oracle and/or its affiliates. */
+
+#include <test_progs.h>
+#include "test_uprobe_autoattach.skel.h"
+
+/* uprobe attach point */
+static noinline int autoattach_trigger_func(int arg)
+{
+	asm volatile ("");
+	return arg + 1;
+}
+
+void test_uprobe_autoattach(void)
+{
+	struct test_uprobe_autoattach *skel;
+	int trigger_val = 100, trigger_ret;
+	size_t malloc_sz = 1;
+	char *mem;
+
+	skel = test_uprobe_autoattach__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(test_uprobe_autoattach__attach(skel), "skel_attach"))
+		goto cleanup;
+
+	skel->bss->test_pid = getpid();
+
+	/* trigger & validate uprobe & uretprobe */
+	trigger_ret = autoattach_trigger_func(trigger_val);
+
+	skel->bss->test_pid = getpid();
+
+	/* trigger & validate shared library u[ret]probes attached by name */
+	mem = malloc(malloc_sz);
+	free(mem);
+
+	ASSERT_EQ(skel->bss->uprobe_byname_parm1, trigger_val, "check_uprobe_byname_parm1");
+	ASSERT_EQ(skel->bss->uprobe_byname_ran, 1, "check_uprobe_byname_ran");
+	ASSERT_EQ(skel->bss->uretprobe_byname_rc, trigger_ret, "check_uretprobe_byname_rc");
+	ASSERT_EQ(skel->bss->uretprobe_byname_ran, 2, "check_uretprobe_byname_ran");
+	ASSERT_EQ(skel->bss->uprobe_byname2_parm1, malloc_sz, "check_uprobe_byname2_parm1");
+	ASSERT_EQ(skel->bss->uprobe_byname2_ran, 3, "check_uprobe_byname2_ran");
+	ASSERT_EQ(skel->bss->uretprobe_byname2_rc, mem, "check_uretprobe_byname2_rc");
+	ASSERT_EQ(skel->bss->uretprobe_byname2_ran, 4, "check_uretprobe_byname2_ran");
+cleanup:
+	test_uprobe_autoattach__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/usdt.c b/tools/testing/selftests/bpf/prog_tests/usdt.c
new file mode 100644
index 000000000000..a71f51bdc08d
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/usdt.c
@@ -0,0 +1,421 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include <test_progs.h>
+
+#define _SDT_HAS_SEMAPHORES 1
+#include "../sdt.h"
+
+#include "test_usdt.skel.h"
+#include "test_urandom_usdt.skel.h"
+
+int lets_test_this(int);
+
+static volatile int idx = 2;
+static volatile __u64 bla = 0xFEDCBA9876543210ULL;
+static volatile short nums[] = {-1, -2, -3, };
+
+static volatile struct {
+	int x;
+	signed char y;
+} t1 = { 1, -127 };
+
+#define SEC(name) __attribute__((section(name), used))
+
+unsigned short test_usdt0_semaphore SEC(".probes");
+unsigned short test_usdt3_semaphore SEC(".probes");
+unsigned short test_usdt12_semaphore SEC(".probes");
+
+static void __always_inline trigger_func(int x) {
+	long y = 42;
+
+	if (test_usdt0_semaphore)
+		STAP_PROBE(test, usdt0);
+	if (test_usdt3_semaphore)
+		STAP_PROBE3(test, usdt3, x, y, &bla);
+	if (test_usdt12_semaphore) {
+		STAP_PROBE12(test, usdt12,
+			     x, x + 1, y, x + y, 5,
+			     y / 7, bla, &bla, -9, nums[x],
+			     nums[idx], t1.y);
+	}
+}
+
+static void subtest_basic_usdt(void)
+{
+	LIBBPF_OPTS(bpf_usdt_opts, opts);
+	struct test_usdt *skel;
+	struct test_usdt__bss *bss;
+	int err;
+
+	skel = test_usdt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bss = skel->bss;
+	bss->my_pid = getpid();
+
+	err = test_usdt__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* usdt0 won't be auto-attached */
+	opts.usdt_cookie = 0xcafedeadbeeffeed;
+	skel->links.usdt0 = bpf_program__attach_usdt(skel->progs.usdt0,
+						     0 /*self*/, "/proc/self/exe",
+						     "test", "usdt0", &opts);
+	if (!ASSERT_OK_PTR(skel->links.usdt0, "usdt0_link"))
+		goto cleanup;
+
+	trigger_func(1);
+
+	ASSERT_EQ(bss->usdt0_called, 1, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, 1, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, 1, "usdt12_called");
+
+	ASSERT_EQ(bss->usdt0_cookie, 0xcafedeadbeeffeed, "usdt0_cookie");
+	ASSERT_EQ(bss->usdt0_arg_cnt, 0, "usdt0_arg_cnt");
+	ASSERT_EQ(bss->usdt0_arg_ret, -ENOENT, "usdt0_arg_ret");
+
+	/* auto-attached usdt3 gets default zero cookie value */
+	ASSERT_EQ(bss->usdt3_cookie, 0, "usdt3_cookie");
+	ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
+
+	ASSERT_EQ(bss->usdt3_arg_rets[0], 0, "usdt3_arg1_ret");
+	ASSERT_EQ(bss->usdt3_arg_rets[1], 0, "usdt3_arg2_ret");
+	ASSERT_EQ(bss->usdt3_arg_rets[2], 0, "usdt3_arg3_ret");
+	ASSERT_EQ(bss->usdt3_args[0], 1, "usdt3_arg1");
+	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
+	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+
+	/* auto-attached usdt12 gets default zero cookie value */
+	ASSERT_EQ(bss->usdt12_cookie, 0, "usdt12_cookie");
+	ASSERT_EQ(bss->usdt12_arg_cnt, 12, "usdt12_arg_cnt");
+
+	ASSERT_EQ(bss->usdt12_args[0], 1, "usdt12_arg1");
+	ASSERT_EQ(bss->usdt12_args[1], 1 + 1, "usdt12_arg2");
+	ASSERT_EQ(bss->usdt12_args[2], 42, "usdt12_arg3");
+	ASSERT_EQ(bss->usdt12_args[3], 42 + 1, "usdt12_arg4");
+	ASSERT_EQ(bss->usdt12_args[4], 5, "usdt12_arg5");
+	ASSERT_EQ(bss->usdt12_args[5], 42 / 7, "usdt12_arg6");
+	ASSERT_EQ(bss->usdt12_args[6], bla, "usdt12_arg7");
+	ASSERT_EQ(bss->usdt12_args[7], (uintptr_t)&bla, "usdt12_arg8");
+	ASSERT_EQ(bss->usdt12_args[8], -9, "usdt12_arg9");
+	ASSERT_EQ(bss->usdt12_args[9], nums[1], "usdt12_arg10");
+	ASSERT_EQ(bss->usdt12_args[10], nums[idx], "usdt12_arg11");
+	ASSERT_EQ(bss->usdt12_args[11], t1.y, "usdt12_arg12");
+
+	/* trigger_func() is marked __always_inline, so USDT invocations will be
+	 * inlined in two different places, meaning that each USDT will have
+	 * at least 2 different places to be attached to. This verifies that
+	 * bpf_program__attach_usdt() handles this properly and attaches to
+	 * all possible places of USDT invocation.
+	 */
+	trigger_func(2);
+
+	ASSERT_EQ(bss->usdt0_called, 2, "usdt0_called");
+	ASSERT_EQ(bss->usdt3_called, 2, "usdt3_called");
+	ASSERT_EQ(bss->usdt12_called, 2, "usdt12_called");
+
+	/* only check values that depend on trigger_func()'s input value */
+	ASSERT_EQ(bss->usdt3_args[0], 2, "usdt3_arg1");
+
+	ASSERT_EQ(bss->usdt12_args[0], 2, "usdt12_arg1");
+	ASSERT_EQ(bss->usdt12_args[1], 2 + 1, "usdt12_arg2");
+	ASSERT_EQ(bss->usdt12_args[3], 42 + 2, "usdt12_arg4");
+	ASSERT_EQ(bss->usdt12_args[9], nums[2], "usdt12_arg10");
+
+	/* detach and re-attach usdt3 */
+	bpf_link__destroy(skel->links.usdt3);
+
+	opts.usdt_cookie = 0xBADC00C51E;
+	skel->links.usdt3 = bpf_program__attach_usdt(skel->progs.usdt3, -1 /* any pid */,
+						     "/proc/self/exe", "test", "usdt3", &opts);
+	if (!ASSERT_OK_PTR(skel->links.usdt3, "usdt3_reattach"))
+		goto cleanup;
+
+	trigger_func(3);
+
+	ASSERT_EQ(bss->usdt3_called, 3, "usdt3_called");
+	/* this time usdt3 has custom cookie */
+	ASSERT_EQ(bss->usdt3_cookie, 0xBADC00C51E, "usdt3_cookie");
+	ASSERT_EQ(bss->usdt3_arg_cnt, 3, "usdt3_arg_cnt");
+
+	ASSERT_EQ(bss->usdt3_arg_rets[0], 0, "usdt3_arg1_ret");
+	ASSERT_EQ(bss->usdt3_arg_rets[1], 0, "usdt3_arg2_ret");
+	ASSERT_EQ(bss->usdt3_arg_rets[2], 0, "usdt3_arg3_ret");
+	ASSERT_EQ(bss->usdt3_args[0], 3, "usdt3_arg1");
+	ASSERT_EQ(bss->usdt3_args[1], 42, "usdt3_arg2");
+	ASSERT_EQ(bss->usdt3_args[2], (uintptr_t)&bla, "usdt3_arg3");
+
+cleanup:
+	test_usdt__destroy(skel);
+}
+
+unsigned short test_usdt_100_semaphore SEC(".probes");
+unsigned short test_usdt_300_semaphore SEC(".probes");
+unsigned short test_usdt_400_semaphore SEC(".probes");
+
+#define R10(F, X)  F(X+0); F(X+1);F(X+2); F(X+3); F(X+4); \
+		   F(X+5); F(X+6); F(X+7); F(X+8); F(X+9);
+#define R100(F, X) R10(F,X+ 0);R10(F,X+10);R10(F,X+20);R10(F,X+30);R10(F,X+40); \
+		   R10(F,X+50);R10(F,X+60);R10(F,X+70);R10(F,X+80);R10(F,X+90);
+
+/* carefully control that we get exactly 100 inlines by preventing inlining */
+static void __always_inline f100(int x)
+{
+	STAP_PROBE1(test, usdt_100, x);
+}
+
+__weak void trigger_100_usdts(void)
+{
+	R100(f100, 0);
+}
+
+/* we shouldn't be able to attach to test:usdt2_300 USDT as we don't have as
+ * many slots for specs. It's important that each STAP_PROBE2() invocation
+ * (after untolling) gets different arg spec due to compiler inlining i as
+ * a constant
+ */
+static void __always_inline f300(int x)
+{
+	STAP_PROBE1(test, usdt_300, x);
+}
+
+__weak void trigger_300_usdts(void)
+{
+	R100(f300, 0);
+	R100(f300, 100);
+	R100(f300, 200);
+}
+
+static void __always_inline f400(int x __attribute__((unused)))
+{
+	static int y;
+
+	STAP_PROBE1(test, usdt_400, y++);
+}
+
+/* this time we have 400 different USDT call sites, but they have uniform
+ * argument location, so libbpf's spec string deduplication logic should keep
+ * spec count use very small and so we should be able to attach to all 400
+ * call sites
+ */
+__weak void trigger_400_usdts(void)
+{
+	R100(f400, 0);
+	R100(f400, 100);
+	R100(f400, 200);
+	R100(f400, 300);
+}
+
+static void subtest_multispec_usdt(void)
+{
+	LIBBPF_OPTS(bpf_usdt_opts, opts);
+	struct test_usdt *skel;
+	struct test_usdt__bss *bss;
+	int err, i;
+
+	skel = test_usdt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	bss = skel->bss;
+	bss->my_pid = getpid();
+
+	err = test_usdt__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* usdt_100 is auto-attached and there are 100 inlined call sites,
+	 * let's validate that all of them are properly attached to and
+	 * handled from BPF side
+	 */
+	trigger_100_usdts();
+
+	ASSERT_EQ(bss->usdt_100_called, 100, "usdt_100_called");
+	ASSERT_EQ(bss->usdt_100_sum, 99 * 100 / 2, "usdt_100_sum");
+
+	/* Stress test free spec ID tracking. By default libbpf allows up to
+	 * 256 specs to be used, so if we don't return free spec IDs back
+	 * after few detachments and re-attachments we should run out of
+	 * available spec IDs.
+	 */
+	for (i = 0; i < 2; i++) {
+		bpf_link__destroy(skel->links.usdt_100);
+
+		skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1,
+							        "/proc/self/exe",
+								"test", "usdt_100", NULL);
+		if (!ASSERT_OK_PTR(skel->links.usdt_100, "usdt_100_reattach"))
+			goto cleanup;
+
+		bss->usdt_100_sum = 0;
+		trigger_100_usdts();
+
+		ASSERT_EQ(bss->usdt_100_called, (i + 1) * 100 + 100, "usdt_100_called");
+		ASSERT_EQ(bss->usdt_100_sum, 99 * 100 / 2, "usdt_100_sum");
+	}
+
+	/* Now let's step it up and try to attach USDT that requires more than
+	 * 256 attach points with different specs for each.
+	 * Note that we need trigger_300_usdts() only to actually have 300
+	 * USDT call sites, we are not going to actually trace them.
+	 */
+	trigger_300_usdts();
+
+	/* we'll reuse usdt_100 BPF program for usdt_300 test */
+	bpf_link__destroy(skel->links.usdt_100);
+	skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1, "/proc/self/exe",
+							"test", "usdt_300", NULL);
+	err = -errno;
+	if (!ASSERT_ERR_PTR(skel->links.usdt_100, "usdt_300_bad_attach"))
+		goto cleanup;
+	ASSERT_EQ(err, -E2BIG, "usdt_300_attach_err");
+
+	/* let's check that there are no "dangling" BPF programs attached due
+	 * to partial success of the above test:usdt_300 attachment
+	 */
+	bss->usdt_100_called = 0;
+	bss->usdt_100_sum = 0;
+
+	f300(777); /* this is 301st instance of usdt_300 */
+
+	ASSERT_EQ(bss->usdt_100_called, 0, "usdt_301_called");
+	ASSERT_EQ(bss->usdt_100_sum, 0, "usdt_301_sum");
+
+	/* This time we have USDT with 400 inlined invocations, but arg specs
+	 * should be the same across all sites, so libbpf will only need to
+	 * use one spec and thus we'll be able to attach 400 uprobes
+	 * successfully.
+	 *
+	 * Again, we are reusing usdt_100 BPF program.
+	 */
+	skel->links.usdt_100 = bpf_program__attach_usdt(skel->progs.usdt_100, -1,
+							"/proc/self/exe",
+							"test", "usdt_400", NULL);
+	if (!ASSERT_OK_PTR(skel->links.usdt_100, "usdt_400_attach"))
+		goto cleanup;
+
+	trigger_400_usdts();
+
+	ASSERT_EQ(bss->usdt_100_called, 400, "usdt_400_called");
+	ASSERT_EQ(bss->usdt_100_sum, 399 * 400 / 2, "usdt_400_sum");
+
+cleanup:
+	test_usdt__destroy(skel);
+}
+
+static FILE *urand_spawn(int *pid)
+{
+	FILE *f;
+
+	/* urandom_read's stdout is wired into f */
+	f = popen("./urandom_read 1 report-pid", "r");
+	if (!f)
+		return NULL;
+
+	if (fscanf(f, "%d", pid) != 1) {
+		pclose(f);
+		return NULL;
+	}
+
+	return f;
+}
+
+static int urand_trigger(FILE **urand_pipe)
+{
+	int exit_code;
+
+	/* pclose() waits for child process to exit and returns their exit code */
+	exit_code = pclose(*urand_pipe);
+	*urand_pipe = NULL;
+
+	return exit_code;
+}
+
+static void subtest_urandom_usdt(bool auto_attach)
+{
+	struct test_urandom_usdt *skel;
+	struct test_urandom_usdt__bss *bss;
+	struct bpf_link *l;
+	FILE *urand_pipe = NULL;
+	int err, urand_pid = 0;
+
+	skel = test_urandom_usdt__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	urand_pipe = urand_spawn(&urand_pid);
+	if (!ASSERT_OK_PTR(urand_pipe, "urand_spawn"))
+		goto cleanup;
+
+	bss = skel->bss;
+	bss->urand_pid = urand_pid;
+
+	if (auto_attach) {
+		err = test_urandom_usdt__attach(skel);
+		if (!ASSERT_OK(err, "skel_auto_attach"))
+			goto cleanup;
+	} else {
+		l = bpf_program__attach_usdt(skel->progs.urand_read_without_sema,
+					     urand_pid, "./urandom_read",
+					     "urand", "read_without_sema", NULL);
+		if (!ASSERT_OK_PTR(l, "urand_without_sema_attach"))
+			goto cleanup;
+		skel->links.urand_read_without_sema = l;
+
+		l = bpf_program__attach_usdt(skel->progs.urand_read_with_sema,
+					     urand_pid, "./urandom_read",
+					     "urand", "read_with_sema", NULL);
+		if (!ASSERT_OK_PTR(l, "urand_with_sema_attach"))
+			goto cleanup;
+		skel->links.urand_read_with_sema = l;
+
+		l = bpf_program__attach_usdt(skel->progs.urandlib_read_without_sema,
+					     urand_pid, "./liburandom_read.so",
+					     "urandlib", "read_without_sema", NULL);
+		if (!ASSERT_OK_PTR(l, "urandlib_without_sema_attach"))
+			goto cleanup;
+		skel->links.urandlib_read_without_sema = l;
+
+		l = bpf_program__attach_usdt(skel->progs.urandlib_read_with_sema,
+					     urand_pid, "./liburandom_read.so",
+					     "urandlib", "read_with_sema", NULL);
+		if (!ASSERT_OK_PTR(l, "urandlib_with_sema_attach"))
+			goto cleanup;
+		skel->links.urandlib_read_with_sema = l;
+
+	}
+
+	/* trigger urandom_read USDTs */
+	ASSERT_OK(urand_trigger(&urand_pipe), "urand_exit_code");
+
+	ASSERT_EQ(bss->urand_read_without_sema_call_cnt, 1, "urand_wo_sema_cnt");
+	ASSERT_EQ(bss->urand_read_without_sema_buf_sz_sum, 256, "urand_wo_sema_sum");
+
+	ASSERT_EQ(bss->urand_read_with_sema_call_cnt, 1, "urand_w_sema_cnt");
+	ASSERT_EQ(bss->urand_read_with_sema_buf_sz_sum, 256, "urand_w_sema_sum");
+
+	ASSERT_EQ(bss->urandlib_read_without_sema_call_cnt, 1, "urandlib_wo_sema_cnt");
+	ASSERT_EQ(bss->urandlib_read_without_sema_buf_sz_sum, 256, "urandlib_wo_sema_sum");
+
+	ASSERT_EQ(bss->urandlib_read_with_sema_call_cnt, 1, "urandlib_w_sema_cnt");
+	ASSERT_EQ(bss->urandlib_read_with_sema_buf_sz_sum, 256, "urandlib_w_sema_sum");
+
+cleanup:
+	if (urand_pipe)
+		pclose(urand_pipe);
+	test_urandom_usdt__destroy(skel);
+}
+
+void test_usdt(void)
+{
+	if (test__start_subtest("basic"))
+		subtest_basic_usdt();
+	if (test__start_subtest("multispec"))
+		subtest_multispec_usdt();
+	if (test__start_subtest("urand_auto_attach"))
+		subtest_urandom_usdt(true /* auto_attach */);
+	if (test__start_subtest("urand_pid_attach"))
+		subtest_urandom_usdt(false /* auto_attach */);
+}
diff --git a/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c b/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c
new file mode 100644
index 000000000000..8e545865ea33
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/for_each_map_elem_write_key.c
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__type(value, __u64);
+} array_map SEC(".maps");
+
+static __u64
+check_array_elem(struct bpf_map *map, __u32 *key, __u64 *val,
+		 void *data)
+{
+	bpf_get_current_comm(key, sizeof(*key));
+	return 0;
+}
+
+SEC("raw_tp/sys_enter")
+int test_map_key_write(const void *ctx)
+{
+	bpf_for_each_map_elem(&array_map, check_array_elem, NULL, 0);
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs1.c b/tools/testing/selftests/bpf/progs/linked_funcs1.c
index b964ec1390c2..963b393c37e8 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs1.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs1.c
@@ -4,6 +4,7 @@
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
 
 /* weak and shared between two files */
 const volatile int my_tid __weak;
@@ -44,6 +45,13 @@ void set_output_ctx1(__u64 *ctx)
 /* this weak instance should win because it's the first one */
 __weak int set_output_weak(int x)
 {
+	static volatile int whatever;
+
+	/* make sure we use CO-RE relocations in a weak function, this used to
+	 * cause problems for BPF static linker
+	 */
+	whatever = bpf_core_type_size(struct task_struct);
+
 	output_weak1 = x;
 	return x;
 }
diff --git a/tools/testing/selftests/bpf/progs/linked_funcs2.c b/tools/testing/selftests/bpf/progs/linked_funcs2.c
index 575e958e60b7..db195872f4eb 100644
--- a/tools/testing/selftests/bpf/progs/linked_funcs2.c
+++ b/tools/testing/selftests/bpf/progs/linked_funcs2.c
@@ -4,6 +4,7 @@
 #include "vmlinux.h"
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
+#include <bpf/bpf_core_read.h>
 
 /* weak and shared between both files */
 const volatile int my_tid __weak;
@@ -44,6 +45,13 @@ void set_output_ctx2(__u64 *ctx)
 /* this weak instance should lose, because it will be processed second */
 __weak int set_output_weak(int x)
 {
+	static volatile int whatever;
+
+	/* make sure we use CO-RE relocations in a weak function, this used to
+	 * cause problems for BPF static linker
+	 */
+	whatever = 2 * bpf_core_type_size(struct task_struct);
+
 	output_weak2 = x;
 	return 2 * x;
 }
diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
index b3fcb5274ee0..f793280a3238 100644
--- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
+++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
@@ -35,10 +35,10 @@ int oncpu(void *ctx)
 	long val;
 
 	val = bpf_get_stackid(ctx, &stackmap, 0);
-	if (val > 0)
+	if (val >= 0)
 		stackid_kernel = 2;
 	val = bpf_get_stackid(ctx, &stackmap, BPF_F_USER_STACK);
-	if (val > 0)
+	if (val >= 0)
 		stackid_user = 2;
 
 	trace = bpf_map_lookup_elem(&stackdata_map, &key);
diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h
index 4896fdf816f7..92331053dba3 100644
--- a/tools/testing/selftests/bpf/progs/profiler.inc.h
+++ b/tools/testing/selftests/bpf/progs/profiler.inc.h
@@ -826,8 +826,9 @@ out:
 
 SEC("kprobe/vfs_link")
 int BPF_KPROBE(kprobe__vfs_link,
-	       struct dentry* old_dentry, struct inode* dir,
-	       struct dentry* new_dentry, struct inode** delegated_inode)
+	       struct dentry* old_dentry, struct user_namespace *mnt_userns,
+	       struct inode* dir, struct dentry* new_dentry,
+	       struct inode** delegated_inode)
 {
 	struct bpf_func_stats_ctx stats_ctx;
 	bpf_stats_enter(&stats_ctx, profiler_bpf_vfs_link);
diff --git a/tools/testing/selftests/bpf/progs/test_attach_probe.c b/tools/testing/selftests/bpf/progs/test_attach_probe.c
index 8056a4c6d918..af994d16bb10 100644
--- a/tools/testing/selftests/bpf/progs/test_attach_probe.c
+++ b/tools/testing/selftests/bpf/progs/test_attach_probe.c
@@ -10,6 +10,10 @@ int kprobe_res = 0;
 int kretprobe_res = 0;
 int uprobe_res = 0;
 int uretprobe_res = 0;
+int uprobe_byname_res = 0;
+int uretprobe_byname_res = 0;
+int uprobe_byname2_res = 0;
+int uretprobe_byname2_res = 0;
 
 SEC("kprobe/sys_nanosleep")
 int handle_kprobe(struct pt_regs *ctx)
@@ -25,18 +29,51 @@ int BPF_KRETPROBE(handle_kretprobe)
 	return 0;
 }
 
-SEC("uprobe/trigger_func")
+SEC("uprobe")
 int handle_uprobe(struct pt_regs *ctx)
 {
 	uprobe_res = 3;
 	return 0;
 }
 
-SEC("uretprobe/trigger_func")
+SEC("uretprobe")
 int handle_uretprobe(struct pt_regs *ctx)
 {
 	uretprobe_res = 4;
 	return 0;
 }
 
+SEC("uprobe")
+int handle_uprobe_byname(struct pt_regs *ctx)
+{
+	uprobe_byname_res = 5;
+	return 0;
+}
+
+/* use auto-attach format for section definition. */
+SEC("uretprobe//proc/self/exe:trigger_func2")
+int handle_uretprobe_byname(struct pt_regs *ctx)
+{
+	uretprobe_byname_res = 6;
+	return 0;
+}
+
+SEC("uprobe")
+int handle_uprobe_byname2(struct pt_regs *ctx)
+{
+	unsigned int size = PT_REGS_PARM1(ctx);
+
+	/* verify malloc size */
+	if (size == 1)
+		uprobe_byname2_res = 7;
+	return 0;
+}
+
+SEC("uretprobe")
+int handle_uretprobe_byname2(struct pt_regs *ctx)
+{
+	uretprobe_byname2_res = 8;
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
index 2d3a7710e2ce..0e2222968918 100644
--- a/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
+++ b/tools/testing/selftests/bpf/progs/test_bpf_cookie.c
@@ -37,14 +37,14 @@ int handle_kretprobe(struct pt_regs *ctx)
 	return 0;
 }
 
-SEC("uprobe/trigger_func")
+SEC("uprobe")
 int handle_uprobe(struct pt_regs *ctx)
 {
 	update(ctx, &uprobe_res);
 	return 0;
 }
 
-SEC("uretprobe/trigger_func")
+SEC("uretprobe")
 int handle_uretprobe(struct pt_regs *ctx)
 {
 	update(ctx, &uretprobe_res);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func17.c b/tools/testing/selftests/bpf/progs/test_global_func17.c
new file mode 100644
index 000000000000..2b8b9b8ba018
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_func17.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+
+__noinline int foo(int *p)
+{
+	return p ? (*p = 42) : 0;
+}
+
+const volatile int i;
+
+SEC("tc")
+int test_cls(struct __sk_buff *skb)
+{
+	return foo((int *)&i);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
index 2180c41cd890..a72a5bf3812a 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_btf_write_check.c
@@ -8,7 +8,7 @@
 extern const int bpf_prog_active __ksym; /* int type global var. */
 
 SEC("raw_tp/sys_enter")
-int handler(const void *ctx)
+int handler1(const void *ctx)
 {
 	int *active;
 	__u32 cpu;
@@ -26,4 +26,20 @@ int handler(const void *ctx)
 	return 0;
 }
 
+__noinline int write_active(int *p)
+{
+	return p ? (*p = 42) : 0;
+}
+
+SEC("raw_tp/sys_enter")
+int handler2(const void *ctx)
+{
+	int *active;
+	__u32 cpu;
+
+	active = bpf_this_cpu_ptr(&bpf_prog_active);
+	write_active(active);
+	return 0;
+}
+
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
index 19e4d2071c60..c8bc0c6947aa 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb_noinline.c
@@ -218,7 +218,7 @@ static __noinline bool get_packet_dst(struct real_definition **real,
 
 	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
 	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
-		return 0;
+		return false;
 
 	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
 	if (!real_pos)
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c
index 02f79356d5eb..98c6493d9b91 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_assign.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -89,7 +89,6 @@ get_tuple(struct __sk_buff *skb, bool *ipv4, bool *tcp)
 static inline int
 handle_udp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 {
-	struct bpf_sock_tuple ln = {0};
 	struct bpf_sock *sk;
 	const int zero = 0;
 	size_t tuple_len;
@@ -121,7 +120,6 @@ assign:
 static inline int
 handle_tcp(struct __sk_buff *skb, struct bpf_sock_tuple *tuple, bool ipv4)
 {
-	struct bpf_sock_tuple ln = {0};
 	struct bpf_sock *sk;
 	const int zero = 0;
 	size_t tuple_len;
@@ -161,7 +159,7 @@ assign:
 SEC("tc")
 int bpf_sk_assign_test(struct __sk_buff *skb)
 {
-	struct bpf_sock_tuple *tuple, ln = {0};
+	struct bpf_sock_tuple *tuple;
 	bool ipv4 = false;
 	bool tcp = false;
 	int tuple_len;
diff --git a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
index e6cb09259408..1926facba122 100644
--- a/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
+++ b/tools/testing/selftests/bpf/progs/test_task_pt_regs.c
@@ -14,7 +14,7 @@ char current_regs[PT_REGS_SIZE] = {};
 char ctx_regs[PT_REGS_SIZE] = {};
 int uprobe_res = 0;
 
-SEC("uprobe/trigger_func")
+SEC("uprobe")
 int handle_uprobe(struct pt_regs *ctx)
 {
 	struct task_struct *current;
diff --git a/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
new file mode 100644
index 000000000000..ab75522e2eeb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_uprobe_autoattach.c
@@ -0,0 +1,73 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, Oracle and/or its affiliates. */
+
+#include "vmlinux.h"
+
+#include <bpf/bpf_core_read.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+int uprobe_byname_parm1 = 0;
+int uprobe_byname_ran = 0;
+int uretprobe_byname_rc = 0;
+int uretprobe_byname_ran = 0;
+size_t uprobe_byname2_parm1 = 0;
+int uprobe_byname2_ran = 0;
+char *uretprobe_byname2_rc = NULL;
+int uretprobe_byname2_ran = 0;
+
+int test_pid;
+
+/* This program cannot auto-attach, but that should not stop other
+ * programs from attaching.
+ */
+SEC("uprobe")
+int handle_uprobe_noautoattach(struct pt_regs *ctx)
+{
+	return 0;
+}
+
+SEC("uprobe//proc/self/exe:autoattach_trigger_func")
+int handle_uprobe_byname(struct pt_regs *ctx)
+{
+	uprobe_byname_parm1 = PT_REGS_PARM1_CORE(ctx);
+	uprobe_byname_ran = 1;
+	return 0;
+}
+
+SEC("uretprobe//proc/self/exe:autoattach_trigger_func")
+int handle_uretprobe_byname(struct pt_regs *ctx)
+{
+	uretprobe_byname_rc = PT_REGS_RC_CORE(ctx);
+	uretprobe_byname_ran = 2;
+	return 0;
+}
+
+
+SEC("uprobe/libc.so.6:malloc")
+int handle_uprobe_byname2(struct pt_regs *ctx)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid)
+		return 0;
+	uprobe_byname2_parm1 = PT_REGS_PARM1_CORE(ctx);
+	uprobe_byname2_ran = 3;
+	return 0;
+}
+
+SEC("uretprobe/libc.so.6:malloc")
+int handle_uretprobe_byname2(struct pt_regs *ctx)
+{
+	int pid = bpf_get_current_pid_tgid() >> 32;
+
+	/* ignore irrelevant invocations */
+	if (test_pid != pid)
+		return 0;
+	uretprobe_byname2_rc = (char *)PT_REGS_RC_CORE(ctx);
+	uretprobe_byname2_ran = 4;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_urandom_usdt.c b/tools/testing/selftests/bpf/progs/test_urandom_usdt.c
new file mode 100644
index 000000000000..3539b02bd5f7
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_urandom_usdt.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+int urand_pid;
+
+int urand_read_without_sema_call_cnt;
+int urand_read_without_sema_buf_sz_sum;
+
+SEC("usdt/./urandom_read:urand:read_without_sema")
+int BPF_USDT(urand_read_without_sema, int iter_num, int iter_cnt, int buf_sz)
+{
+	if (urand_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&urand_read_without_sema_call_cnt, 1);
+	__sync_fetch_and_add(&urand_read_without_sema_buf_sz_sum, buf_sz);
+
+	return 0;
+}
+
+int urand_read_with_sema_call_cnt;
+int urand_read_with_sema_buf_sz_sum;
+
+SEC("usdt/./urandom_read:urand:read_with_sema")
+int BPF_USDT(urand_read_with_sema, int iter_num, int iter_cnt, int buf_sz)
+{
+	if (urand_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&urand_read_with_sema_call_cnt, 1);
+	__sync_fetch_and_add(&urand_read_with_sema_buf_sz_sum, buf_sz);
+
+	return 0;
+}
+
+int urandlib_read_without_sema_call_cnt;
+int urandlib_read_without_sema_buf_sz_sum;
+
+SEC("usdt/./liburandom_read.so:urandlib:read_without_sema")
+int BPF_USDT(urandlib_read_without_sema, int iter_num, int iter_cnt, int buf_sz)
+{
+	if (urand_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&urandlib_read_without_sema_call_cnt, 1);
+	__sync_fetch_and_add(&urandlib_read_without_sema_buf_sz_sum, buf_sz);
+
+	return 0;
+}
+
+int urandlib_read_with_sema_call_cnt;
+int urandlib_read_with_sema_buf_sz_sum;
+
+SEC("usdt/./liburandom_read.so:urandlib:read_with_sema")
+int BPF_USDT(urandlib_read_with_sema, int iter_num, int iter_cnt, int buf_sz)
+{
+	if (urand_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&urandlib_read_with_sema_call_cnt, 1);
+	__sync_fetch_and_add(&urandlib_read_with_sema_buf_sz_sum, buf_sz);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_usdt.c b/tools/testing/selftests/bpf/progs/test_usdt.c
new file mode 100644
index 000000000000..505aab9a5234
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_usdt.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+int my_pid;
+
+int usdt0_called;
+u64 usdt0_cookie;
+int usdt0_arg_cnt;
+int usdt0_arg_ret;
+
+SEC("usdt")
+int usdt0(struct pt_regs *ctx)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt0_called, 1);
+
+	usdt0_cookie = bpf_usdt_cookie(ctx);
+	usdt0_arg_cnt = bpf_usdt_arg_cnt(ctx);
+	/* should return -ENOENT for any arg_num */
+	usdt0_arg_ret = bpf_usdt_arg(ctx, bpf_get_prandom_u32(), &tmp);
+	return 0;
+}
+
+int usdt3_called;
+u64 usdt3_cookie;
+int usdt3_arg_cnt;
+int usdt3_arg_rets[3];
+u64 usdt3_args[3];
+
+SEC("usdt//proc/self/exe:test:usdt3")
+int usdt3(struct pt_regs *ctx)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt3_called, 1);
+
+	usdt3_cookie = bpf_usdt_cookie(ctx);
+	usdt3_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+	usdt3_arg_rets[0] = bpf_usdt_arg(ctx, 0, &tmp);
+	usdt3_args[0] = (int)tmp;
+
+	usdt3_arg_rets[1] = bpf_usdt_arg(ctx, 1, &tmp);
+	usdt3_args[1] = (long)tmp;
+
+	usdt3_arg_rets[2] = bpf_usdt_arg(ctx, 2, &tmp);
+	usdt3_args[2] = (uintptr_t)tmp;
+
+	return 0;
+}
+
+int usdt12_called;
+u64 usdt12_cookie;
+int usdt12_arg_cnt;
+u64 usdt12_args[12];
+
+SEC("usdt//proc/self/exe:test:usdt12")
+int BPF_USDT(usdt12, int a1, int a2, long a3, long a4, unsigned a5,
+		     long a6, __u64 a7, uintptr_t a8, int a9, short a10,
+		     short a11, signed char a12)
+{
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt12_called, 1);
+
+	usdt12_cookie = bpf_usdt_cookie(ctx);
+	usdt12_arg_cnt = bpf_usdt_arg_cnt(ctx);
+
+	usdt12_args[0] = a1;
+	usdt12_args[1] = a2;
+	usdt12_args[2] = a3;
+	usdt12_args[3] = a4;
+	usdt12_args[4] = a5;
+	usdt12_args[5] = a6;
+	usdt12_args[6] = a7;
+	usdt12_args[7] = a8;
+	usdt12_args[8] = a9;
+	usdt12_args[9] = a10;
+	usdt12_args[10] = a11;
+	usdt12_args[11] = a12;
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_usdt_multispec.c b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c
new file mode 100644
index 000000000000..aa6de32b50d1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_usdt_multispec.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/usdt.bpf.h>
+
+/* this file is linked together with test_usdt.c to validate that usdt.bpf.h
+ * can be included in multiple .bpf.c files forming single final BPF object
+ * file
+ */
+
+extern int my_pid;
+
+int usdt_100_called;
+int usdt_100_sum;
+
+SEC("usdt//proc/self/exe:test:usdt_100")
+int BPF_USDT(usdt_100, int x)
+{
+	long tmp;
+
+	if (my_pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
+
+	__sync_fetch_and_add(&usdt_100_called, 1);
+	__sync_fetch_and_add(&usdt_100_sum, x);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 596c4e71bf3a..125d872d7981 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -564,22 +564,22 @@ static bool get_packet_dst(struct real_definition **real,
 	hash = get_packet_hash(pckt, hash_16bytes);
 	if (hash != 0x358459b7 /* jhash of ipv4 packet */  &&
 	    hash != 0x2f4bc6bb /* jhash of ipv6 packet */)
-		return 0;
+		return false;
 	key = 2 * vip_info->vip_num + hash % 2;
 	real_pos = bpf_map_lookup_elem(&ch_rings, &key);
 	if (!real_pos)
-		return 0;
+		return false;
 	key = *real_pos;
 	*real = bpf_map_lookup_elem(&reals, &key);
 	if (!(*real))
-		return 0;
+		return false;
 	if (!(vip_info->flags & (1 << 1))) {
 		__u32 conn_rate_key = 512 + 2;
 		struct lb_stats *conn_rate_stats =
 		    bpf_map_lookup_elem(&stats, &conn_rate_key);
 
 		if (!conn_rate_stats)
-			return 1;
+			return true;
 		cur_time = bpf_ktime_get_ns();
 		if ((cur_time - conn_rate_stats->v2) >> 32 > 0xffFFFF) {
 			conn_rate_stats->v1 = 1;
@@ -587,14 +587,14 @@ static bool get_packet_dst(struct real_definition **real,
 		} else {
 			conn_rate_stats->v1 += 1;
 			if (conn_rate_stats->v1 >= 1)
-				return 1;
+				return true;
 		}
 		if (pckt->flow.proto == IPPROTO_UDP)
 			new_dst_lru.atime = cur_time;
 		new_dst_lru.pos = key;
 		bpf_map_update_elem(lru_map, &pckt->flow, &new_dst_lru, 0);
 	}
-	return 1;
+	return true;
 }
 
 __attribute__ ((noinline))
diff --git a/tools/testing/selftests/bpf/progs/trigger_bench.c b/tools/testing/selftests/bpf/progs/trigger_bench.c
index 2ab049b54d6c..694e7cec1823 100644
--- a/tools/testing/selftests/bpf/progs/trigger_bench.c
+++ b/tools/testing/selftests/bpf/progs/trigger_bench.c
@@ -54,7 +54,7 @@ int bench_trigger_fmodret(void *ctx)
 	return -22;
 }
 
-SEC("uprobe/self/uprobe_target")
+SEC("uprobe")
 int bench_trigger_uprobe(void *ctx)
 {
 	__sync_add_and_fetch(&hits, 1);
diff --git a/tools/testing/selftests/bpf/sdt-config.h b/tools/testing/selftests/bpf/sdt-config.h
new file mode 100644
index 000000000000..733045a52771
--- /dev/null
+++ b/tools/testing/selftests/bpf/sdt-config.h
@@ -0,0 +1,6 @@
+/* includes/sys/sdt-config.h.  Generated from sdt-config.h.in by configure.
+
+   This file just defines _SDT_ASM_SECTION_AUTOGROUP_SUPPORT to 0 or 1 to
+   indicate whether the assembler supports "?" in .pushsection directives.  */
+
+#define _SDT_ASM_SECTION_AUTOGROUP_SUPPORT 1
diff --git a/tools/testing/selftests/bpf/sdt.h b/tools/testing/selftests/bpf/sdt.h
new file mode 100644
index 000000000000..ca0162b4dc57
--- /dev/null
+++ b/tools/testing/selftests/bpf/sdt.h
@@ -0,0 +1,513 @@
+/* <sys/sdt.h> - Systemtap static probe definition macros.
+
+   This file is dedicated to the public domain, pursuant to CC0
+   (https://creativecommons.org/publicdomain/zero/1.0/)
+*/
+
+#ifndef _SYS_SDT_H
+#define _SYS_SDT_H    1
+
+/*
+  This file defines a family of macros
+
+       STAP_PROBEn(op1, ..., opn)
+
+  that emit a nop into the instruction stream, and some data into an auxiliary
+  note section.  The data in the note section describes the operands, in terms
+  of size and location.  Each location is encoded as assembler operand string.
+  Consumer tools such as gdb or systemtap insert breakpoints on top of
+  the nop, and decode the location operand-strings, like an assembler,
+  to find the values being passed.
+
+  The operand strings are selected by the compiler for each operand.
+  They are constrained by gcc inline-assembler codes.  The default is:
+
+  #define STAP_SDT_ARG_CONSTRAINT nor
+
+  This is a good default if the operands tend to be integral and
+  moderate in number (smaller than number of registers).  In other
+  cases, the compiler may report "'asm' requires impossible reload" or
+  similar.  In this case, consider simplifying the macro call (fewer
+  and simpler operands), reduce optimization, or override the default
+  constraints string via:
+
+  #define STAP_SDT_ARG_CONSTRAINT g
+  #include <sys/sdt.h>
+
+  See also:
+  https://sourceware.org/systemtap/wiki/UserSpaceProbeImplementation
+  https://gcc.gnu.org/onlinedocs/gcc/Constraints.html
+ */
+
+
+
+#ifdef __ASSEMBLER__
+# define _SDT_PROBE(provider, name, n, arglist)	\
+  _SDT_ASM_BODY(provider, name, _SDT_ASM_SUBSTR_1, (_SDT_DEPAREN_##n arglist)) \
+  _SDT_ASM_BASE
+# define _SDT_ASM_1(x)			x;
+# define _SDT_ASM_2(a, b)		a,b;
+# define _SDT_ASM_3(a, b, c)		a,b,c;
+# define _SDT_ASM_5(a, b, c, d, e)	a,b,c,d,e;
+# define _SDT_ASM_STRING_1(x)		.asciz #x;
+# define _SDT_ASM_SUBSTR_1(x)		.ascii #x;
+# define _SDT_DEPAREN_0()				/* empty */
+# define _SDT_DEPAREN_1(a)				a
+# define _SDT_DEPAREN_2(a,b)				a b
+# define _SDT_DEPAREN_3(a,b,c)				a b c
+# define _SDT_DEPAREN_4(a,b,c,d)			a b c d
+# define _SDT_DEPAREN_5(a,b,c,d,e)			a b c d e
+# define _SDT_DEPAREN_6(a,b,c,d,e,f)			a b c d e f
+# define _SDT_DEPAREN_7(a,b,c,d,e,f,g)			a b c d e f g
+# define _SDT_DEPAREN_8(a,b,c,d,e,f,g,h)		a b c d e f g h
+# define _SDT_DEPAREN_9(a,b,c,d,e,f,g,h,i)		a b c d e f g h i
+# define _SDT_DEPAREN_10(a,b,c,d,e,f,g,h,i,j)		a b c d e f g h i j
+# define _SDT_DEPAREN_11(a,b,c,d,e,f,g,h,i,j,k)		a b c d e f g h i j k
+# define _SDT_DEPAREN_12(a,b,c,d,e,f,g,h,i,j,k,l)	a b c d e f g h i j k l
+#else
+#if defined _SDT_HAS_SEMAPHORES
+#define _SDT_NOTE_SEMAPHORE_USE(provider, name) \
+  __asm__ __volatile__ ("" :: "m" (provider##_##name##_semaphore));
+#else
+#define _SDT_NOTE_SEMAPHORE_USE(provider, name)
+#endif
+
+# define _SDT_PROBE(provider, name, n, arglist) \
+  do {									    \
+    _SDT_NOTE_SEMAPHORE_USE(provider, name); \
+    __asm__ __volatile__ (_SDT_ASM_BODY(provider, name, _SDT_ASM_ARGS, (n)) \
+			  :: _SDT_ASM_OPERANDS_##n arglist);		    \
+    __asm__ __volatile__ (_SDT_ASM_BASE);				    \
+  } while (0)
+# define _SDT_S(x)			#x
+# define _SDT_ASM_1(x)			_SDT_S(x) "\n"
+# define _SDT_ASM_2(a, b)		_SDT_S(a) "," _SDT_S(b) "\n"
+# define _SDT_ASM_3(a, b, c)		_SDT_S(a) "," _SDT_S(b) "," \
+					_SDT_S(c) "\n"
+# define _SDT_ASM_5(a, b, c, d, e)	_SDT_S(a) "," _SDT_S(b) "," \
+					_SDT_S(c) "," _SDT_S(d) "," \
+					_SDT_S(e) "\n"
+# define _SDT_ASM_ARGS(n)		_SDT_ASM_TEMPLATE_##n
+# define _SDT_ASM_STRING_1(x)		_SDT_ASM_1(.asciz #x)
+# define _SDT_ASM_SUBSTR_1(x)		_SDT_ASM_1(.ascii #x)
+
+# define _SDT_ARGFMT(no)                _SDT_ASM_1(_SDT_SIGN %n[_SDT_S##no]) \
+                                        _SDT_ASM_1(_SDT_SIZE %n[_SDT_S##no]) \
+                                        _SDT_ASM_1(_SDT_TYPE %n[_SDT_S##no]) \
+                                        _SDT_ASM_SUBSTR(_SDT_ARGTMPL(_SDT_A##no))
+
+
+# ifndef STAP_SDT_ARG_CONSTRAINT
+# if defined __powerpc__
+# define STAP_SDT_ARG_CONSTRAINT        nZr
+# elif defined __arm__
+# define STAP_SDT_ARG_CONSTRAINT        g
+# else
+# define STAP_SDT_ARG_CONSTRAINT        nor
+# endif
+# endif
+
+# define _SDT_STRINGIFY(x)              #x
+# define _SDT_ARG_CONSTRAINT_STRING(x)  _SDT_STRINGIFY(x)
+/* _SDT_S encodes the size and type as 0xSSTT which is decoded by the assembler
+   macros _SDT_SIZE and _SDT_TYPE */
+# define _SDT_ARG(n, x)				    \
+  [_SDT_S##n] "n" ((_SDT_ARGSIGNED (x) ? (int)-1 : 1) * (-(((int) _SDT_ARGSIZE (x)) << 8) + (-(0x7f & __builtin_classify_type (x))))), \
+  [_SDT_A##n] _SDT_ARG_CONSTRAINT_STRING (STAP_SDT_ARG_CONSTRAINT) (_SDT_ARGVAL (x))
+#endif
+#define _SDT_ASM_STRING(x)		_SDT_ASM_STRING_1(x)
+#define _SDT_ASM_SUBSTR(x)		_SDT_ASM_SUBSTR_1(x)
+
+#define _SDT_ARGARRAY(x)	(__builtin_classify_type (x) == 14	\
+				 || __builtin_classify_type (x) == 5)
+
+#ifdef __cplusplus
+# define _SDT_ARGSIGNED(x)	(!_SDT_ARGARRAY (x) \
+				 && __sdt_type<__typeof (x)>::__sdt_signed)
+# define _SDT_ARGSIZE(x)	(_SDT_ARGARRAY (x) \
+				 ? sizeof (void *) : sizeof (x))
+# define _SDT_ARGVAL(x)		(x)
+
+# include <cstddef>
+
+template<typename __sdt_T>
+struct __sdt_type
+{
+  static const bool __sdt_signed = false;
+};
+  
+#define __SDT_ALWAYS_SIGNED(T) \
+template<> struct __sdt_type<T> { static const bool __sdt_signed = true; };
+#define __SDT_COND_SIGNED(T,CT)						\
+template<> struct __sdt_type<T> { static const bool __sdt_signed = ((CT)(-1) < 1); };
+__SDT_ALWAYS_SIGNED(signed char)
+__SDT_ALWAYS_SIGNED(short)
+__SDT_ALWAYS_SIGNED(int)
+__SDT_ALWAYS_SIGNED(long)
+__SDT_ALWAYS_SIGNED(long long)
+__SDT_ALWAYS_SIGNED(volatile signed char)
+__SDT_ALWAYS_SIGNED(volatile short)
+__SDT_ALWAYS_SIGNED(volatile int)
+__SDT_ALWAYS_SIGNED(volatile long)
+__SDT_ALWAYS_SIGNED(volatile long long)
+__SDT_ALWAYS_SIGNED(const signed char)
+__SDT_ALWAYS_SIGNED(const short)
+__SDT_ALWAYS_SIGNED(const int)
+__SDT_ALWAYS_SIGNED(const long)
+__SDT_ALWAYS_SIGNED(const long long)
+__SDT_ALWAYS_SIGNED(const volatile signed char)
+__SDT_ALWAYS_SIGNED(const volatile short)
+__SDT_ALWAYS_SIGNED(const volatile int)
+__SDT_ALWAYS_SIGNED(const volatile long)
+__SDT_ALWAYS_SIGNED(const volatile long long)
+__SDT_COND_SIGNED(char, char)
+__SDT_COND_SIGNED(wchar_t, wchar_t)
+__SDT_COND_SIGNED(volatile char, char)
+__SDT_COND_SIGNED(volatile wchar_t, wchar_t)
+__SDT_COND_SIGNED(const char, char)
+__SDT_COND_SIGNED(const wchar_t, wchar_t)
+__SDT_COND_SIGNED(const volatile char, char)
+__SDT_COND_SIGNED(const volatile wchar_t, wchar_t)
+#if defined (__GNUC__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 4))
+/* __SDT_COND_SIGNED(char16_t) */
+/* __SDT_COND_SIGNED(char32_t) */
+#endif
+
+template<typename __sdt_E>
+struct __sdt_type<__sdt_E[]> : public __sdt_type<__sdt_E *> {};
+
+template<typename __sdt_E, size_t __sdt_N>
+struct __sdt_type<__sdt_E[__sdt_N]> : public __sdt_type<__sdt_E *> {};
+
+#elif !defined(__ASSEMBLER__)
+__extension__ extern unsigned long long __sdt_unsp;
+# define _SDT_ARGINTTYPE(x)						\
+  __typeof (__builtin_choose_expr (((__builtin_classify_type (x)	\
+				     + 3) & -4) == 4, (x), 0U))
+# define _SDT_ARGSIGNED(x)						\
+  (!__extension__							\
+   (__builtin_constant_p ((((unsigned long long)			\
+			    (_SDT_ARGINTTYPE (x)) __sdt_unsp)		\
+			   & ((unsigned long long)1 << (sizeof (unsigned long long)	\
+				       * __CHAR_BIT__ - 1))) == 0)	\
+    || (_SDT_ARGINTTYPE (x)) -1 > (_SDT_ARGINTTYPE (x)) 0))
+# define _SDT_ARGSIZE(x)	\
+  (_SDT_ARGARRAY (x) ? sizeof (void *) : sizeof (x))
+# define _SDT_ARGVAL(x)		(x)
+#endif
+
+#if defined __powerpc__ || defined __powerpc64__
+# define _SDT_ARGTMPL(id)	%I[id]%[id]
+#elif defined __i386__
+# define _SDT_ARGTMPL(id)	%k[id]  /* gcc.gnu.org/PR80115 sourceware.org/PR24541 */
+#else
+# define _SDT_ARGTMPL(id)	%[id]
+#endif
+
+/* NB: gdb PR24541 highlighted an unspecified corner of the sdt.h
+   operand note format.
+
+   The named register may be a longer or shorter (!) alias for the
+   storage where the value in question is found.  For example, on
+   i386, 64-bit value may be put in register pairs, and the register
+   name stored would identify just one of them.  Previously, gcc was
+   asked to emit the %w[id] (16-bit alias of some registers holding
+   operands), even when a wider 32-bit value was used.
+
+   Bottom line: the byte-width given before the @ sign governs.  If
+   there is a mismatch between that width and that of the named
+   register, then a sys/sdt.h note consumer may need to employ
+   architecture-specific heuristics to figure out where the compiler
+   has actually put the complete value.
+*/
+
+#ifdef __LP64__
+# define _SDT_ASM_ADDR	.8byte
+#else
+# define _SDT_ASM_ADDR	.4byte
+#endif
+
+/* The ia64 and s390 nop instructions take an argument. */
+#if defined(__ia64__) || defined(__s390__) || defined(__s390x__)
+#define _SDT_NOP	nop 0
+#else
+#define _SDT_NOP	nop
+#endif
+
+#define _SDT_NOTE_NAME	"stapsdt"
+#define _SDT_NOTE_TYPE	3
+
+/* If the assembler supports the necessary feature, then we can play
+   nice with code in COMDAT sections, which comes up in C++ code.
+   Without that assembler support, some combinations of probe placements
+   in certain kinds of C++ code may produce link-time errors.  */
+#include "sdt-config.h"
+#if _SDT_ASM_SECTION_AUTOGROUP_SUPPORT
+# define _SDT_ASM_AUTOGROUP "?"
+#else
+# define _SDT_ASM_AUTOGROUP ""
+#endif
+
+#define _SDT_DEF_MACROS							     \
+	_SDT_ASM_1(.altmacro)						     \
+	_SDT_ASM_1(.macro _SDT_SIGN x)				     	     \
+	_SDT_ASM_3(.pushsection .note.stapsdt,"","note")		     \
+	_SDT_ASM_1(.iflt \\x)						     \
+	_SDT_ASM_1(.ascii "-")						     \
+	_SDT_ASM_1(.endif)						     \
+	_SDT_ASM_1(.popsection)						     \
+	_SDT_ASM_1(.endm)						     \
+	_SDT_ASM_1(.macro _SDT_SIZE_ x)					     \
+	_SDT_ASM_3(.pushsection .note.stapsdt,"","note")		     \
+	_SDT_ASM_1(.ascii "\x")						     \
+	_SDT_ASM_1(.popsection)						     \
+	_SDT_ASM_1(.endm)						     \
+	_SDT_ASM_1(.macro _SDT_SIZE x)					     \
+	_SDT_ASM_1(_SDT_SIZE_ %%((-(-\\x*((-\\x>0)-(-\\x<0))))>>8))	     \
+	_SDT_ASM_1(.endm)						     \
+	_SDT_ASM_1(.macro _SDT_TYPE_ x)				             \
+	_SDT_ASM_3(.pushsection .note.stapsdt,"","note")		     \
+	_SDT_ASM_2(.ifc 8,\\x)					     	     \
+	_SDT_ASM_1(.ascii "f")						     \
+	_SDT_ASM_1(.endif)						     \
+	_SDT_ASM_1(.ascii "@")						     \
+	_SDT_ASM_1(.popsection)						     \
+	_SDT_ASM_1(.endm)						     \
+	_SDT_ASM_1(.macro _SDT_TYPE x)				     	     \
+	_SDT_ASM_1(_SDT_TYPE_ %%((\\x)&(0xff)))			     \
+	_SDT_ASM_1(.endm)
+
+#define _SDT_UNDEF_MACROS						      \
+  _SDT_ASM_1(.purgem _SDT_SIGN)						      \
+  _SDT_ASM_1(.purgem _SDT_SIZE_)					      \
+  _SDT_ASM_1(.purgem _SDT_SIZE)						      \
+  _SDT_ASM_1(.purgem _SDT_TYPE_)					      \
+  _SDT_ASM_1(.purgem _SDT_TYPE)
+
+#define _SDT_ASM_BODY(provider, name, pack_args, args, ...)		      \
+  _SDT_DEF_MACROS							      \
+  _SDT_ASM_1(990:	_SDT_NOP)					      \
+  _SDT_ASM_3(		.pushsection .note.stapsdt,_SDT_ASM_AUTOGROUP,"note") \
+  _SDT_ASM_1(		.balign 4)					      \
+  _SDT_ASM_3(		.4byte 992f-991f, 994f-993f, _SDT_NOTE_TYPE)	      \
+  _SDT_ASM_1(991:	.asciz _SDT_NOTE_NAME)				      \
+  _SDT_ASM_1(992:	.balign 4)					      \
+  _SDT_ASM_1(993:	_SDT_ASM_ADDR 990b)				      \
+  _SDT_ASM_1(		_SDT_ASM_ADDR _.stapsdt.base)			      \
+  _SDT_SEMAPHORE(provider,name)						      \
+  _SDT_ASM_STRING(provider)						      \
+  _SDT_ASM_STRING(name)							      \
+  pack_args args							      \
+  _SDT_ASM_SUBSTR(\x00)							      \
+  _SDT_UNDEF_MACROS							      \
+  _SDT_ASM_1(994:	.balign 4)					      \
+  _SDT_ASM_1(		.popsection)
+
+#define _SDT_ASM_BASE							      \
+  _SDT_ASM_1(.ifndef _.stapsdt.base)					      \
+  _SDT_ASM_5(		.pushsection .stapsdt.base,"aG","progbits",	      \
+							.stapsdt.base,comdat) \
+  _SDT_ASM_1(		.weak _.stapsdt.base)				      \
+  _SDT_ASM_1(		.hidden _.stapsdt.base)				      \
+  _SDT_ASM_1(	_.stapsdt.base: .space 1)				      \
+  _SDT_ASM_2(		.size _.stapsdt.base, 1)			      \
+  _SDT_ASM_1(		.popsection)					      \
+  _SDT_ASM_1(.endif)
+
+#if defined _SDT_HAS_SEMAPHORES
+#define _SDT_SEMAPHORE(p,n) \
+	_SDT_ASM_1(		_SDT_ASM_ADDR p##_##n##_semaphore)
+#else
+#define _SDT_SEMAPHORE(p,n) _SDT_ASM_1(		_SDT_ASM_ADDR 0)
+#endif
+
+#define _SDT_ASM_BLANK _SDT_ASM_SUBSTR(\x20)
+#define _SDT_ASM_TEMPLATE_0		/* no arguments */
+#define _SDT_ASM_TEMPLATE_1		_SDT_ARGFMT(1)
+#define _SDT_ASM_TEMPLATE_2		_SDT_ASM_TEMPLATE_1 _SDT_ASM_BLANK _SDT_ARGFMT(2)
+#define _SDT_ASM_TEMPLATE_3		_SDT_ASM_TEMPLATE_2 _SDT_ASM_BLANK _SDT_ARGFMT(3)
+#define _SDT_ASM_TEMPLATE_4		_SDT_ASM_TEMPLATE_3 _SDT_ASM_BLANK _SDT_ARGFMT(4)
+#define _SDT_ASM_TEMPLATE_5		_SDT_ASM_TEMPLATE_4 _SDT_ASM_BLANK _SDT_ARGFMT(5)
+#define _SDT_ASM_TEMPLATE_6		_SDT_ASM_TEMPLATE_5 _SDT_ASM_BLANK _SDT_ARGFMT(6)
+#define _SDT_ASM_TEMPLATE_7		_SDT_ASM_TEMPLATE_6 _SDT_ASM_BLANK _SDT_ARGFMT(7)
+#define _SDT_ASM_TEMPLATE_8		_SDT_ASM_TEMPLATE_7 _SDT_ASM_BLANK _SDT_ARGFMT(8)
+#define _SDT_ASM_TEMPLATE_9		_SDT_ASM_TEMPLATE_8 _SDT_ASM_BLANK _SDT_ARGFMT(9)
+#define _SDT_ASM_TEMPLATE_10		_SDT_ASM_TEMPLATE_9 _SDT_ASM_BLANK _SDT_ARGFMT(10)
+#define _SDT_ASM_TEMPLATE_11		_SDT_ASM_TEMPLATE_10 _SDT_ASM_BLANK _SDT_ARGFMT(11)
+#define _SDT_ASM_TEMPLATE_12		_SDT_ASM_TEMPLATE_11 _SDT_ASM_BLANK _SDT_ARGFMT(12)
+#define _SDT_ASM_OPERANDS_0()		[__sdt_dummy] "g" (0)
+#define _SDT_ASM_OPERANDS_1(arg1)	_SDT_ARG(1, arg1)
+#define _SDT_ASM_OPERANDS_2(arg1, arg2) \
+  _SDT_ASM_OPERANDS_1(arg1), _SDT_ARG(2, arg2)
+#define _SDT_ASM_OPERANDS_3(arg1, arg2, arg3) \
+  _SDT_ASM_OPERANDS_2(arg1, arg2), _SDT_ARG(3, arg3)
+#define _SDT_ASM_OPERANDS_4(arg1, arg2, arg3, arg4) \
+  _SDT_ASM_OPERANDS_3(arg1, arg2, arg3), _SDT_ARG(4, arg4)
+#define _SDT_ASM_OPERANDS_5(arg1, arg2, arg3, arg4, arg5) \
+  _SDT_ASM_OPERANDS_4(arg1, arg2, arg3, arg4), _SDT_ARG(5, arg5)
+#define _SDT_ASM_OPERANDS_6(arg1, arg2, arg3, arg4, arg5, arg6) \
+  _SDT_ASM_OPERANDS_5(arg1, arg2, arg3, arg4, arg5), _SDT_ARG(6, arg6)
+#define _SDT_ASM_OPERANDS_7(arg1, arg2, arg3, arg4, arg5, arg6, arg7) \
+  _SDT_ASM_OPERANDS_6(arg1, arg2, arg3, arg4, arg5, arg6), _SDT_ARG(7, arg7)
+#define _SDT_ASM_OPERANDS_8(arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8) \
+  _SDT_ASM_OPERANDS_7(arg1, arg2, arg3, arg4, arg5, arg6, arg7), \
+    _SDT_ARG(8, arg8)
+#define _SDT_ASM_OPERANDS_9(arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9) \
+  _SDT_ASM_OPERANDS_8(arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8), \
+    _SDT_ARG(9, arg9)
+#define _SDT_ASM_OPERANDS_10(arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10) \
+  _SDT_ASM_OPERANDS_9(arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9), \
+    _SDT_ARG(10, arg10)
+#define _SDT_ASM_OPERANDS_11(arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11) \
+  _SDT_ASM_OPERANDS_10(arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9, arg10), \
+    _SDT_ARG(11, arg11)
+#define _SDT_ASM_OPERANDS_12(arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11,arg12) \
+  _SDT_ASM_OPERANDS_11(arg1, arg2, arg3, arg4, arg5, arg6, arg7, arg8, arg9, arg10, arg11), \
+    _SDT_ARG(12, arg12)
+
+/* These macros can be used in C, C++, or assembly code.
+   In assembly code the arguments should use normal assembly operand syntax.  */
+
+#define STAP_PROBE(provider, name) \
+  _SDT_PROBE(provider, name, 0, ())
+#define STAP_PROBE1(provider, name, arg1) \
+  _SDT_PROBE(provider, name, 1, (arg1))
+#define STAP_PROBE2(provider, name, arg1, arg2) \
+  _SDT_PROBE(provider, name, 2, (arg1, arg2))
+#define STAP_PROBE3(provider, name, arg1, arg2, arg3) \
+  _SDT_PROBE(provider, name, 3, (arg1, arg2, arg3))
+#define STAP_PROBE4(provider, name, arg1, arg2, arg3, arg4) \
+  _SDT_PROBE(provider, name, 4, (arg1, arg2, arg3, arg4))
+#define STAP_PROBE5(provider, name, arg1, arg2, arg3, arg4, arg5) \
+  _SDT_PROBE(provider, name, 5, (arg1, arg2, arg3, arg4, arg5))
+#define STAP_PROBE6(provider, name, arg1, arg2, arg3, arg4, arg5, arg6)	\
+  _SDT_PROBE(provider, name, 6, (arg1, arg2, arg3, arg4, arg5, arg6))
+#define STAP_PROBE7(provider, name, arg1, arg2, arg3, arg4, arg5, arg6, arg7) \
+  _SDT_PROBE(provider, name, 7, (arg1, arg2, arg3, arg4, arg5, arg6, arg7))
+#define STAP_PROBE8(provider,name,arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8) \
+  _SDT_PROBE(provider, name, 8, (arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8))
+#define STAP_PROBE9(provider,name,arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9)\
+  _SDT_PROBE(provider, name, 9, (arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9))
+#define STAP_PROBE10(provider,name,arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10) \
+  _SDT_PROBE(provider, name, 10, \
+	     (arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10))
+#define STAP_PROBE11(provider,name,arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11) \
+  _SDT_PROBE(provider, name, 11, \
+	     (arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11))
+#define STAP_PROBE12(provider,name,arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11,arg12) \
+  _SDT_PROBE(provider, name, 12, \
+	     (arg1,arg2,arg3,arg4,arg5,arg6,arg7,arg8,arg9,arg10,arg11,arg12))
+
+/* This STAP_PROBEV macro can be used in variadic scenarios, where the
+   number of probe arguments is not known until compile time.  Since
+   variadic macro support may vary with compiler options, you must
+   pre-#define SDT_USE_VARIADIC to enable this type of probe.
+
+   The trick to count __VA_ARGS__ was inspired by this post by
+   Laurent Deniau <laurent.deniau@cern.ch>:
+       http://groups.google.com/group/comp.std.c/msg/346fc464319b1ee5
+
+   Note that our _SDT_NARG is called with an extra 0 arg that's not
+   counted, so we don't have to worry about the behavior of macros
+   called without any arguments.  */
+
+#define _SDT_NARG(...) __SDT_NARG(__VA_ARGS__, 12,11,10,9,8,7,6,5,4,3,2,1,0)
+#define __SDT_NARG(_0,_1,_2,_3,_4,_5,_6,_7,_8,_9,_10,_11,_12, N, ...) N
+#ifdef SDT_USE_VARIADIC
+#define _SDT_PROBE_N(provider, name, N, ...) \
+  _SDT_PROBE(provider, name, N, (__VA_ARGS__))
+#define STAP_PROBEV(provider, name, ...) \
+  _SDT_PROBE_N(provider, name, _SDT_NARG(0, ##__VA_ARGS__), ##__VA_ARGS__)
+#endif
+
+/* These macros are for use in asm statements.  You must compile
+   with -std=gnu99 or -std=c99 to use the STAP_PROBE_ASM macro.
+
+   The STAP_PROBE_ASM macro generates a quoted string to be used in the
+   template portion of the asm statement, concatenated with strings that
+   contain the actual assembly code around the probe site.
+
+   For example:
+
+	asm ("before\n"
+	     STAP_PROBE_ASM(provider, fooprobe, %eax 4(%esi))
+	     "after");
+
+   emits the assembly code for "before\nafter", with a probe in between.
+   The probe arguments are the %eax register, and the value of the memory
+   word located 4 bytes past the address in the %esi register.  Note that
+   because this is a simple asm, not a GNU C extended asm statement, these
+   % characters do not need to be doubled to generate literal %reg names.
+
+   In a GNU C extended asm statement, the probe arguments can be specified
+   using the macro STAP_PROBE_ASM_TEMPLATE(n) for n arguments.  The paired
+   macro STAP_PROBE_ASM_OPERANDS gives the C values of these probe arguments,
+   and appears in the input operand list of the asm statement.  For example:
+
+	asm ("someinsn %0,%1\n" // %0 is output operand, %1 is input operand
+	     STAP_PROBE_ASM(provider, fooprobe, STAP_PROBE_ASM_TEMPLATE(3))
+	     "otherinsn %[namedarg]"
+	     : "r" (outvar)
+	     : "g" (some_value), [namedarg] "i" (1234),
+	       STAP_PROBE_ASM_OPERANDS(3, some_value, some_ptr->field, 1234));
+
+    This is just like writing:
+
+	STAP_PROBE3(provider, fooprobe, some_value, some_ptr->field, 1234));
+
+    but the probe site is right between "someinsn" and "otherinsn".
+
+    The probe arguments in STAP_PROBE_ASM can be given as assembly
+    operands instead, even inside a GNU C extended asm statement.
+    Note that these can use operand templates like %0 or %[name],
+    and likewise they must write %%reg for a literal operand of %reg.  */
+
+#define _SDT_ASM_BODY_1(p,n,...) _SDT_ASM_BODY(p,n,_SDT_ASM_SUBSTR,(__VA_ARGS__))
+#define _SDT_ASM_BODY_2(p,n,...) _SDT_ASM_BODY(p,n,/*_SDT_ASM_STRING */,__VA_ARGS__)
+#define _SDT_ASM_BODY_N2(p,n,no,...) _SDT_ASM_BODY_ ## no(p,n,__VA_ARGS__)
+#define _SDT_ASM_BODY_N1(p,n,no,...) _SDT_ASM_BODY_N2(p,n,no,__VA_ARGS__)
+#define _SDT_ASM_BODY_N(p,n,...) _SDT_ASM_BODY_N1(p,n,_SDT_NARG(0, __VA_ARGS__),__VA_ARGS__)
+
+#if __STDC_VERSION__ >= 199901L
+# define STAP_PROBE_ASM(provider, name, ...)		\
+  _SDT_ASM_BODY_N(provider, name, __VA_ARGS__)					\
+  _SDT_ASM_BASE
+# define STAP_PROBE_ASM_OPERANDS(n, ...) _SDT_ASM_OPERANDS_##n(__VA_ARGS__)
+#else
+# define STAP_PROBE_ASM(provider, name, args)	\
+  _SDT_ASM_BODY(provider, name, /* _SDT_ASM_STRING */, (args))	\
+  _SDT_ASM_BASE
+#endif
+#define STAP_PROBE_ASM_TEMPLATE(n) _SDT_ASM_TEMPLATE_##n,"use _SDT_ASM_TEMPLATE_"
+
+
+/* DTrace compatible macro names.  */
+#define DTRACE_PROBE(provider,probe)		\
+  STAP_PROBE(provider,probe)
+#define DTRACE_PROBE1(provider,probe,parm1)	\
+  STAP_PROBE1(provider,probe,parm1)
+#define DTRACE_PROBE2(provider,probe,parm1,parm2)	\
+  STAP_PROBE2(provider,probe,parm1,parm2)
+#define DTRACE_PROBE3(provider,probe,parm1,parm2,parm3) \
+  STAP_PROBE3(provider,probe,parm1,parm2,parm3)
+#define DTRACE_PROBE4(provider,probe,parm1,parm2,parm3,parm4)	\
+  STAP_PROBE4(provider,probe,parm1,parm2,parm3,parm4)
+#define DTRACE_PROBE5(provider,probe,parm1,parm2,parm3,parm4,parm5)	\
+  STAP_PROBE5(provider,probe,parm1,parm2,parm3,parm4,parm5)
+#define DTRACE_PROBE6(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6) \
+  STAP_PROBE6(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6)
+#define DTRACE_PROBE7(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7) \
+  STAP_PROBE7(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7)
+#define DTRACE_PROBE8(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8) \
+  STAP_PROBE8(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8)
+#define DTRACE_PROBE9(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9) \
+  STAP_PROBE9(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9)
+#define DTRACE_PROBE10(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10) \
+  STAP_PROBE10(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10)
+#define DTRACE_PROBE11(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10,parm11) \
+  STAP_PROBE11(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10,parm11)
+#define DTRACE_PROBE12(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10,parm11,parm12) \
+  STAP_PROBE12(provider,probe,parm1,parm2,parm3,parm4,parm5,parm6,parm7,parm8,parm9,parm10,parm11,parm12)
+
+
+#endif /* sys/sdt.h */
diff --git a/tools/testing/selftests/bpf/test_bpftool_synctypes.py b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
index 6bf21e47882a..c0e7acd698ed 100755
--- a/tools/testing/selftests/bpf/test_bpftool_synctypes.py
+++ b/tools/testing/selftests/bpf/test_bpftool_synctypes.py
@@ -180,7 +180,7 @@ class FileExtractor(object):
         @enum_name: name of the enum to parse
         """
         start_marker = re.compile(f'enum {enum_name} {{\n')
-        pattern = re.compile('^\s*(BPF_\w+),?$')
+        pattern = re.compile('^\s*(BPF_\w+),?(\s+/\*.*\*/)?$')
         end_marker = re.compile('^};')
         parser = BlockParser(self.reader)
         parser.search_block(start_marker)
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
index d6a1be4d8020..2ffa08198d1c 100644
--- a/tools/testing/selftests/bpf/test_cgroup_storage.c
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -7,6 +7,7 @@
 #include <sys/sysinfo.h>
 
 #include "bpf_rlimit.h"
+#include "bpf_util.h"
 #include "cgroup_helpers.h"
 #include "testing_helpers.h"
 
@@ -44,7 +45,7 @@ int main(int argc, char **argv)
 	unsigned long long *percpu_value;
 	int cpu, nproc;
 
-	nproc = get_nprocs_conf();
+	nproc = bpf_num_possible_cpus();
 	percpu_value = malloc(sizeof(*percpu_value) * nproc);
 	if (!percpu_value) {
 		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index edaffd43da83..6cd6ef9fc20b 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -184,7 +184,7 @@ def bpftool_prog_list(expected=None, ns=""):
 def bpftool_map_list(expected=None, ns=""):
     _, maps = bpftool("map show", JSON=True, ns=ns, fail=True)
     # Remove the base maps
-    maps = [m for m in maps if m not in base_maps and m.get('name') not in base_map_names]
+    maps = [m for m in maps if m not in base_maps and m.get('name') and m.get('name') not in base_map_names]
     if expected is not None:
         if len(maps) != expected:
             fail(True, "%d BPF maps loaded, expected %d" %
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2ecb73a65206..0a4b45d7b515 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -761,8 +761,10 @@ int cd_flavor_subdir(const char *exec_name)
 	const char *flavor = strrchr(exec_name, '/');
 
 	if (!flavor)
-		return 0;
-	flavor++;
+		flavor = exec_name;
+	else
+		flavor++;
+
 	flavor = strrchr(flavor, '-');
 	if (!flavor)
 		return 0;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 93c1ff705533..eec4c7385b14 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -332,6 +332,8 @@ int trigger_module_test_write(int write_sz);
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
 #elif defined(__s390x__)
 #define SYS_NANOSLEEP_KPROBE_NAME "__s390x_sys_nanosleep"
+#elif defined(__aarch64__)
+#define SYS_NANOSLEEP_KPROBE_NAME "__arm64_sys_nanosleep"
 #else
 #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
 #endif
diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
index 795b6798ccee..87867f7a78c3 100644
--- a/tools/testing/selftests/bpf/testing_helpers.c
+++ b/tools/testing/selftests/bpf/testing_helpers.c
@@ -60,7 +60,7 @@ int parse_num_list(const char *s, bool **num_set, int *num_set_len)
 			set[i] = true;
 	}
 
-	if (!set)
+	if (!set || parsing_end)
 		return -EINVAL;
 
 	*num_set = set;
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 3d6217e3aff7..9c4be2cdb21a 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -25,15 +25,12 @@ static int ksym_cmp(const void *p1, const void *p2)
 
 int load_kallsyms(void)
 {
-	FILE *f = fopen("/proc/kallsyms", "r");
+	FILE *f;
 	char func[256], buf[256];
 	char symbol;
 	void *addr;
 	int i = 0;
 
-	if (!f)
-		return -ENOENT;
-
 	/*
 	 * This is called/used from multiplace places,
 	 * load symbols just once.
@@ -41,6 +38,10 @@ int load_kallsyms(void)
 	if (sym_cnt)
 		return 0;
 
+	f = fopen("/proc/kallsyms", "r");
+	if (!f)
+		return -ENOENT;
+
 	while (fgets(buf, sizeof(buf), f)) {
 		if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3)
 			break;
diff --git a/tools/testing/selftests/bpf/urandom_read.c b/tools/testing/selftests/bpf/urandom_read.c
index db781052758d..e92644d0fa75 100644
--- a/tools/testing/selftests/bpf/urandom_read.c
+++ b/tools/testing/selftests/bpf/urandom_read.c
@@ -1,32 +1,85 @@
+#include <stdbool.h>
 #include <stdio.h>
 #include <unistd.h>
+#include <errno.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <stdlib.h>
+#include <signal.h>
+
+#define _SDT_HAS_SEMAPHORES 1
+#include "sdt.h"
+
+#define SEC(name) __attribute__((section(name), used))
 
 #define BUF_SIZE 256
 
+/* defined in urandom_read_aux.c */
+void urand_read_without_sema(int iter_num, int iter_cnt, int read_sz);
+/* these are coming from urandom_read_lib{1,2}.c */
+void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz);
+void urandlib_read_without_sema(int iter_num, int iter_cnt, int read_sz);
+
+unsigned short urand_read_with_sema_semaphore SEC(".probes");
+
 static __attribute__((noinline))
 void urandom_read(int fd, int count)
 {
-       char buf[BUF_SIZE];
-       int i;
+	char buf[BUF_SIZE];
+	int i;
+
+	for (i = 0; i < count; ++i) {
+		read(fd, buf, BUF_SIZE);
+
+		/* trigger USDTs defined in executable itself */
+		urand_read_without_sema(i, count, BUF_SIZE);
+		STAP_PROBE3(urand, read_with_sema, i, count, BUF_SIZE);
 
-       for (i = 0; i < count; ++i)
-               read(fd, buf, BUF_SIZE);
+		/* trigger USDTs defined in shared lib */
+		urandlib_read_without_sema(i, count, BUF_SIZE);
+		urandlib_read_with_sema(i, count, BUF_SIZE);
+	}
+}
+
+static volatile bool parent_ready;
+
+static void handle_sigpipe(int sig)
+{
+	parent_ready = true;
 }
 
 int main(int argc, char *argv[])
 {
 	int fd = open("/dev/urandom", O_RDONLY);
 	int count = 4;
+	bool report_pid = false;
 
 	if (fd < 0)
 		return 1;
 
-	if (argc == 2)
+	if (argc >= 2)
 		count = atoi(argv[1]);
+	if (argc >= 3) {
+		report_pid = true;
+		/* install SIGPIPE handler to catch when parent closes their
+		 * end of the pipe (on the other side of our stdout)
+		 */
+		signal(SIGPIPE, handle_sigpipe);
+	}
+
+	/* report PID and wait for parent process to send us "signal" by
+	 * closing stdout
+	 */
+	if (report_pid) {
+		while (!parent_ready) {
+			fprintf(stdout, "%d\n", getpid());
+			fflush(stdout);
+		}
+		/* at this point stdout is closed, parent process knows our
+		 * PID and is ready to trace us
+		 */
+	}
 
 	urandom_read(fd, count);
 
diff --git a/tools/testing/selftests/bpf/urandom_read_aux.c b/tools/testing/selftests/bpf/urandom_read_aux.c
new file mode 100644
index 000000000000..6132edcfea74
--- /dev/null
+++ b/tools/testing/selftests/bpf/urandom_read_aux.c
@@ -0,0 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include "sdt.h"
+
+void urand_read_without_sema(int iter_num, int iter_cnt, int read_sz)
+{
+	/* semaphore-less USDT */
+	STAP_PROBE3(urand, read_without_sema, iter_num, iter_cnt, read_sz);
+}
diff --git a/tools/testing/selftests/bpf/urandom_read_lib1.c b/tools/testing/selftests/bpf/urandom_read_lib1.c
new file mode 100644
index 000000000000..86186e24b740
--- /dev/null
+++ b/tools/testing/selftests/bpf/urandom_read_lib1.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#define _SDT_HAS_SEMAPHORES 1
+#include "sdt.h"
+
+#define SEC(name) __attribute__((section(name), used))
+
+unsigned short urandlib_read_with_sema_semaphore SEC(".probes");
+
+void urandlib_read_with_sema(int iter_num, int iter_cnt, int read_sz)
+{
+	STAP_PROBE3(urandlib, read_with_sema, iter_num, iter_cnt, read_sz);
+}
diff --git a/tools/testing/selftests/bpf/urandom_read_lib2.c b/tools/testing/selftests/bpf/urandom_read_lib2.c
new file mode 100644
index 000000000000..9d401ad9838f
--- /dev/null
+++ b/tools/testing/selftests/bpf/urandom_read_lib2.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+#include "sdt.h"
+
+void urandlib_read_without_sema(int iter_num, int iter_cnt, int read_sz)
+{
+	STAP_PROBE3(urandlib, read_without_sema, iter_num, iter_cnt, read_sz);
+}