Merge tag 'probes-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull probes updates from Masami Hiramatsu:
 "Uprobes:

   - x86/shstk: Make return uprobe work with shadow stack

   - Add uretprobe syscall which speeds up the uretprobe 10-30% faster.
     This syscall is automatically used from user-space trampolines
     which are generated by the uretprobe. If this syscall is used by
     normal user program, it will cause SIGILL. Note that this is
     currently only implemented on x86_64.

     (This also has two fixes for adjusting the syscall number to avoid
     conflict with new *attrat syscalls.)

   - uprobes/perf: fix user stack traces in the presence of pending
     uretprobe. This corrects the uretprobe's trampoline address in the
     stacktrace with correct return address

   - selftests/x86: Add a return uprobe with shadow stack test

   - selftests/bpf: Add uretprobe syscall related tests.
      - test case for register integrity check
      - test case with register changing case
      - test case for uretprobe syscall without uprobes (expected to fail)
      - test case for uretprobe with shadow stack

   - selftests/bpf: add test validating uprobe/uretprobe stack traces

   - MAINTAINERS: Add uprobes entry. This does not specify the tree but
     to clarify who maintains and reviews the uprobes

  Kprobes:

   - tracing/kprobes: Test case cleanups.

     Replace redundant WARN_ON_ONCE() + pr_warn() with WARN_ONCE() and
     remove unnecessary code from selftest

   - tracing/kprobes: Add symbol counting check when module loads.

     This checks the uniqueness of the probed symbol on modules. The
     same check has already done for kernel symbols

     (This also has a fix for build error with CONFIG_MODULES=n)

  Cleanup:

   - Add MODULE_DESCRIPTION() macros for fprobe and kprobe examples"

* tag 'probes-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  MAINTAINERS: Add uprobes entry
  selftests/bpf: Change uretprobe syscall number in uprobe_syscall test
  uprobe: Change uretprobe syscall scope and number
  tracing/kprobes: Fix build error when find_module() is not available
  tracing/kprobes: Add symbol counting check when module loads
  selftests/bpf: add test validating uprobe/uretprobe stack traces
  perf,uprobes: fix user stack traces in the presence of pending uretprobes
  tracing/kprobe: Remove cleanup code unrelated to selftest
  tracing/kprobe: Integrate test warnings into WARN_ONCE
  selftests/bpf: Add uretprobe shadow stack test
  selftests/bpf: Add uretprobe syscall call from user space test
  selftests/bpf: Add uretprobe syscall test for regs changes
  selftests/bpf: Add uretprobe syscall test for regs integrity
  selftests/x86: Add return uprobe shadow stack test
  uprobe: Add uretprobe syscall to speed up return probe
  uprobe: Wire up uretprobe system call
  x86/shstk: Make return uprobe work with shadow stack
  samples: kprobes: add missing MODULE_DESCRIPTION() macros
  fprobe: add missing MODULE_DESCRIPTION() macro

8 files changed, 970 insertions, 1 deletions

diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index 8a63a9913495..6f7f22ac9da5 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -62,6 +62,10 @@
 #define __nocf_check __attribute__((nocf_check))
 #endif
 
+#ifndef __naked
+#define __naked __attribute__((__naked__))
+#endif
+
 /* Are two types/vars the same type (ignoring qualifiers)? */
 #ifndef __same_type
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index f8962a1dd397..fd28c1157bd3 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -18,6 +18,7 @@
 #include <linux/in6.h>
 #include <linux/un.h>
 #include <net/sock.h>
+#include <linux/namei.h>
 #include "bpf_testmod.h"
 #include "bpf_testmod_kfunc.h"
 
@@ -413,6 +414,119 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.write = bpf_testmod_test_write,
 };
 
+/* bpf_testmod_uprobe sysfs attribute is so far enabled for x86_64 only,
+ * please see test_uretprobe_regs_change test
+ */
+#ifdef __x86_64__
+
+static int
+uprobe_ret_handler(struct uprobe_consumer *self, unsigned long func,
+		   struct pt_regs *regs)
+
+{
+	regs->ax  = 0x12345678deadbeef;
+	regs->cx  = 0x87654321feebdaed;
+	regs->r11 = (u64) -1;
+	return true;
+}
+
+struct testmod_uprobe {
+	struct path path;
+	loff_t offset;
+	struct uprobe_consumer consumer;
+};
+
+static DEFINE_MUTEX(testmod_uprobe_mutex);
+
+static struct testmod_uprobe uprobe = {
+	.consumer.ret_handler = uprobe_ret_handler,
+};
+
+static int testmod_register_uprobe(loff_t offset)
+{
+	int err = -EBUSY;
+
+	if (uprobe.offset)
+		return -EBUSY;
+
+	mutex_lock(&testmod_uprobe_mutex);
+
+	if (uprobe.offset)
+		goto out;
+
+	err = kern_path("/proc/self/exe", LOOKUP_FOLLOW, &uprobe.path);
+	if (err)
+		goto out;
+
+	err = uprobe_register_refctr(d_real_inode(uprobe.path.dentry),
+				     offset, 0, &uprobe.consumer);
+	if (err)
+		path_put(&uprobe.path);
+	else
+		uprobe.offset = offset;
+
+out:
+	mutex_unlock(&testmod_uprobe_mutex);
+	return err;
+}
+
+static void testmod_unregister_uprobe(void)
+{
+	mutex_lock(&testmod_uprobe_mutex);
+
+	if (uprobe.offset) {
+		uprobe_unregister(d_real_inode(uprobe.path.dentry),
+				  uprobe.offset, &uprobe.consumer);
+		uprobe.offset = 0;
+	}
+
+	mutex_unlock(&testmod_uprobe_mutex);
+}
+
+static ssize_t
+bpf_testmod_uprobe_write(struct file *file, struct kobject *kobj,
+			 struct bin_attribute *bin_attr,
+			 char *buf, loff_t off, size_t len)
+{
+	unsigned long offset = 0;
+	int err = 0;
+
+	if (kstrtoul(buf, 0, &offset))
+		return -EINVAL;
+
+	if (offset)
+		err = testmod_register_uprobe(offset);
+	else
+		testmod_unregister_uprobe();
+
+	return err ?: strlen(buf);
+}
+
+static struct bin_attribute bin_attr_bpf_testmod_uprobe_file __ro_after_init = {
+	.attr = { .name = "bpf_testmod_uprobe", .mode = 0666, },
+	.write = bpf_testmod_uprobe_write,
+};
+
+static int register_bpf_testmod_uprobe(void)
+{
+	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+static void unregister_bpf_testmod_uprobe(void)
+{
+	testmod_unregister_uprobe();
+	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_uprobe_file);
+}
+
+#else
+static int register_bpf_testmod_uprobe(void)
+{
+	return 0;
+}
+
+static void unregister_bpf_testmod_uprobe(void) { }
+#endif
+
 BTF_KFUNCS_START(bpf_testmod_common_kfunc_ids)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_new, KF_ITER_NEW)
 BTF_ID_FLAGS(func, bpf_iter_testmod_seq_next, KF_ITER_NEXT | KF_RET_NULL)
@@ -983,7 +1097,13 @@ static int bpf_testmod_init(void)
 		return -EINVAL;
 	sock = NULL;
 	mutex_init(&sock_lock);
-	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	if (ret < 0)
+		return ret;
+	ret = register_bpf_testmod_uprobe();
+	if (ret < 0)
+		return ret;
+	return 0;
 }
 
 static void bpf_testmod_exit(void)
@@ -998,6 +1118,7 @@ static void bpf_testmod_exit(void)
 
 	bpf_kfunc_close_sock();
 	sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	unregister_bpf_testmod_uprobe();
 }
 
 module_init(bpf_testmod_init);
diff --git a/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
new file mode 100644
index 000000000000..bd8c75b620c2
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+
+#ifdef __x86_64__
+
+#include <unistd.h>
+#include <asm/ptrace.h>
+#include <linux/compiler.h>
+#include <linux/stringify.h>
+#include <sys/wait.h>
+#include <sys/syscall.h>
+#include <sys/prctl.h>
+#include <asm/prctl.h>
+#include "uprobe_syscall.skel.h"
+#include "uprobe_syscall_executed.skel.h"
+
+__naked unsigned long uretprobe_regs_trigger(void)
+{
+	asm volatile (
+		"movq $0xdeadbeef, %rax\n"
+		"ret\n"
+	);
+}
+
+__naked void uretprobe_regs(struct pt_regs *before, struct pt_regs *after)
+{
+	asm volatile (
+		"movq %r15,   0(%rdi)\n"
+		"movq %r14,   8(%rdi)\n"
+		"movq %r13,  16(%rdi)\n"
+		"movq %r12,  24(%rdi)\n"
+		"movq %rbp,  32(%rdi)\n"
+		"movq %rbx,  40(%rdi)\n"
+		"movq %r11,  48(%rdi)\n"
+		"movq %r10,  56(%rdi)\n"
+		"movq  %r9,  64(%rdi)\n"
+		"movq  %r8,  72(%rdi)\n"
+		"movq %rax,  80(%rdi)\n"
+		"movq %rcx,  88(%rdi)\n"
+		"movq %rdx,  96(%rdi)\n"
+		"movq %rsi, 104(%rdi)\n"
+		"movq %rdi, 112(%rdi)\n"
+		"movq   $0, 120(%rdi)\n" /* orig_rax */
+		"movq   $0, 128(%rdi)\n" /* rip      */
+		"movq   $0, 136(%rdi)\n" /* cs       */
+		"pushf\n"
+		"pop %rax\n"
+		"movq %rax, 144(%rdi)\n" /* eflags   */
+		"movq %rsp, 152(%rdi)\n" /* rsp      */
+		"movq   $0, 160(%rdi)\n" /* ss       */
+
+		/* save 2nd argument */
+		"pushq %rsi\n"
+		"call uretprobe_regs_trigger\n"
+
+		/* save  return value and load 2nd argument pointer to rax */
+		"pushq %rax\n"
+		"movq 8(%rsp), %rax\n"
+
+		"movq %r15,   0(%rax)\n"
+		"movq %r14,   8(%rax)\n"
+		"movq %r13,  16(%rax)\n"
+		"movq %r12,  24(%rax)\n"
+		"movq %rbp,  32(%rax)\n"
+		"movq %rbx,  40(%rax)\n"
+		"movq %r11,  48(%rax)\n"
+		"movq %r10,  56(%rax)\n"
+		"movq  %r9,  64(%rax)\n"
+		"movq  %r8,  72(%rax)\n"
+		"movq %rcx,  88(%rax)\n"
+		"movq %rdx,  96(%rax)\n"
+		"movq %rsi, 104(%rax)\n"
+		"movq %rdi, 112(%rax)\n"
+		"movq   $0, 120(%rax)\n" /* orig_rax */
+		"movq   $0, 128(%rax)\n" /* rip      */
+		"movq   $0, 136(%rax)\n" /* cs       */
+
+		/* restore return value and 2nd argument */
+		"pop %rax\n"
+		"pop %rsi\n"
+
+		"movq %rax,  80(%rsi)\n"
+
+		"pushf\n"
+		"pop %rax\n"
+
+		"movq %rax, 144(%rsi)\n" /* eflags   */
+		"movq %rsp, 152(%rsi)\n" /* rsp      */
+		"movq   $0, 160(%rsi)\n" /* ss       */
+		"ret\n"
+);
+}
+
+static void test_uretprobe_regs_equal(void)
+{
+	struct uprobe_syscall *skel = NULL;
+	struct pt_regs before = {}, after = {};
+	unsigned long *pb = (unsigned long *) &before;
+	unsigned long *pa = (unsigned long *) &after;
+	unsigned long *pp;
+	unsigned int i, cnt;
+	int err;
+
+	skel = uprobe_syscall__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall__open_and_load"))
+		goto cleanup;
+
+	err = uprobe_syscall__attach(skel);
+	if (!ASSERT_OK(err, "uprobe_syscall__attach"))
+		goto cleanup;
+
+	uretprobe_regs(&before, &after);
+
+	pp = (unsigned long *) &skel->bss->regs;
+	cnt = sizeof(before)/sizeof(*pb);
+
+	for (i = 0; i < cnt; i++) {
+		unsigned int offset = i * sizeof(unsigned long);
+
+		/*
+		 * Check register before and after uretprobe_regs_trigger call
+		 * that triggers the uretprobe.
+		 */
+		switch (offset) {
+		case offsetof(struct pt_regs, rax):
+			ASSERT_EQ(pa[i], 0xdeadbeef, "return value");
+			break;
+		default:
+			if (!ASSERT_EQ(pb[i], pa[i], "register before-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+
+		/*
+		 * Check register seen from bpf program and register after
+		 * uretprobe_regs_trigger call
+		 */
+		switch (offset) {
+		/*
+		 * These values will be different (not set in uretprobe_regs),
+		 * we don't care.
+		 */
+		case offsetof(struct pt_regs, orig_rax):
+		case offsetof(struct pt_regs, rip):
+		case offsetof(struct pt_regs, cs):
+		case offsetof(struct pt_regs, rsp):
+		case offsetof(struct pt_regs, ss):
+			break;
+		default:
+			if (!ASSERT_EQ(pp[i], pa[i], "register prog-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+	}
+
+cleanup:
+	uprobe_syscall__destroy(skel);
+}
+
+#define BPF_TESTMOD_UPROBE_TEST_FILE "/sys/kernel/bpf_testmod_uprobe"
+
+static int write_bpf_testmod_uprobe(unsigned long offset)
+{
+	size_t n, ret;
+	char buf[30];
+	int fd;
+
+	n = sprintf(buf, "%lu", offset);
+
+	fd = open(BPF_TESTMOD_UPROBE_TEST_FILE, O_WRONLY);
+	if (fd < 0)
+		return -errno;
+
+	ret = write(fd, buf, n);
+	close(fd);
+	return ret != n ? (int) ret : 0;
+}
+
+static void test_uretprobe_regs_change(void)
+{
+	struct pt_regs before = {}, after = {};
+	unsigned long *pb = (unsigned long *) &before;
+	unsigned long *pa = (unsigned long *) &after;
+	unsigned long cnt = sizeof(before)/sizeof(*pb);
+	unsigned int i, err, offset;
+
+	offset = get_uprobe_offset(uretprobe_regs_trigger);
+
+	err = write_bpf_testmod_uprobe(offset);
+	if (!ASSERT_OK(err, "register_uprobe"))
+		return;
+
+	uretprobe_regs(&before, &after);
+
+	err = write_bpf_testmod_uprobe(0);
+	if (!ASSERT_OK(err, "unregister_uprobe"))
+		return;
+
+	for (i = 0; i < cnt; i++) {
+		unsigned int offset = i * sizeof(unsigned long);
+
+		switch (offset) {
+		case offsetof(struct pt_regs, rax):
+			ASSERT_EQ(pa[i], 0x12345678deadbeef, "rax");
+			break;
+		case offsetof(struct pt_regs, rcx):
+			ASSERT_EQ(pa[i], 0x87654321feebdaed, "rcx");
+			break;
+		case offsetof(struct pt_regs, r11):
+			ASSERT_EQ(pa[i], (__u64) -1, "r11");
+			break;
+		default:
+			if (!ASSERT_EQ(pa[i], pb[i], "register before-after value check"))
+				fprintf(stdout, "failed register offset %u\n", offset);
+		}
+	}
+}
+
+#ifndef __NR_uretprobe
+#define __NR_uretprobe 467
+#endif
+
+__naked unsigned long uretprobe_syscall_call_1(void)
+{
+	/*
+	 * Pretend we are uretprobe trampoline to trigger the return
+	 * probe invocation in order to verify we get SIGILL.
+	 */
+	asm volatile (
+		"pushq %rax\n"
+		"pushq %rcx\n"
+		"pushq %r11\n"
+		"movq $" __stringify(__NR_uretprobe) ", %rax\n"
+		"syscall\n"
+		"popq %r11\n"
+		"popq %rcx\n"
+		"retq\n"
+	);
+}
+
+__naked unsigned long uretprobe_syscall_call(void)
+{
+	asm volatile (
+		"call uretprobe_syscall_call_1\n"
+		"retq\n"
+	);
+}
+
+static void test_uretprobe_syscall_call(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_multi_opts, opts,
+		.retprobe = true,
+	);
+	struct uprobe_syscall_executed *skel;
+	int pid, status, err, go[2], c;
+
+	if (ASSERT_OK(pipe(go), "pipe"))
+		return;
+
+	skel = uprobe_syscall_executed__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "uprobe_syscall_executed__open_and_load"))
+		goto cleanup;
+
+	pid = fork();
+	if (!ASSERT_GE(pid, 0, "fork"))
+		goto cleanup;
+
+	/* child */
+	if (pid == 0) {
+		close(go[1]);
+
+		/* wait for parent's kick */
+		err = read(go[0], &c, 1);
+		if (err != 1)
+			exit(-1);
+
+		uretprobe_syscall_call();
+		_exit(0);
+	}
+
+	skel->links.test = bpf_program__attach_uprobe_multi(skel->progs.test, pid,
+							    "/proc/self/exe",
+							    "uretprobe_syscall_call", &opts);
+	if (!ASSERT_OK_PTR(skel->links.test, "bpf_program__attach_uprobe_multi"))
+		goto cleanup;
+
+	/* kick the child */
+	write(go[1], &c, 1);
+	err = waitpid(pid, &status, 0);
+	ASSERT_EQ(err, pid, "waitpid");
+
+	/* verify the child got killed with SIGILL */
+	ASSERT_EQ(WIFSIGNALED(status), 1, "WIFSIGNALED");
+	ASSERT_EQ(WTERMSIG(status), SIGILL, "WTERMSIG");
+
+	/* verify the uretprobe program wasn't called */
+	ASSERT_EQ(skel->bss->executed, 0, "executed");
+
+cleanup:
+	uprobe_syscall_executed__destroy(skel);
+	close(go[1]);
+	close(go[0]);
+}
+
+/*
+ * Borrowed from tools/testing/selftests/x86/test_shadow_stack.c.
+ *
+ * For use in inline enablement of shadow stack.
+ *
+ * The program can't return from the point where shadow stack gets enabled
+ * because there will be no address on the shadow stack. So it can't use
+ * syscall() for enablement, since it is a function.
+ *
+ * Based on code from nolibc.h. Keep a copy here because this can't pull
+ * in all of nolibc.h.
+ */
+#define ARCH_PRCTL(arg1, arg2)					\
+({								\
+	long _ret;						\
+	register long _num  asm("eax") = __NR_arch_prctl;	\
+	register long _arg1 asm("rdi") = (long)(arg1);		\
+	register long _arg2 asm("rsi") = (long)(arg2);		\
+								\
+	asm volatile (						\
+		"syscall\n"					\
+		: "=a"(_ret)					\
+		: "r"(_arg1), "r"(_arg2),			\
+		  "0"(_num)					\
+		: "rcx", "r11", "memory", "cc"			\
+	);							\
+	_ret;							\
+})
+
+#ifndef ARCH_SHSTK_ENABLE
+#define ARCH_SHSTK_ENABLE	0x5001
+#define ARCH_SHSTK_DISABLE	0x5002
+#define ARCH_SHSTK_SHSTK	(1ULL <<  0)
+#endif
+
+static void test_uretprobe_shadow_stack(void)
+{
+	if (ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK)) {
+		test__skip();
+		return;
+	}
+
+	/* Run all of the uretprobe tests. */
+	test_uretprobe_regs_equal();
+	test_uretprobe_regs_change();
+	test_uretprobe_syscall_call();
+
+	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
+}
+#else
+static void test_uretprobe_regs_equal(void)
+{
+	test__skip();
+}
+
+static void test_uretprobe_regs_change(void)
+{
+	test__skip();
+}
+
+static void test_uretprobe_syscall_call(void)
+{
+	test__skip();
+}
+
+static void test_uretprobe_shadow_stack(void)
+{
+	test__skip();
+}
+#endif
+
+void test_uprobe_syscall(void)
+{
+	if (test__start_subtest("uretprobe_regs_equal"))
+		test_uretprobe_regs_equal();
+	if (test__start_subtest("uretprobe_regs_change"))
+		test_uretprobe_regs_change();
+	if (test__start_subtest("uretprobe_syscall_call"))
+		test_uretprobe_syscall_call();
+	if (test__start_subtest("uretprobe_shadow_stack"))
+		test_uretprobe_shadow_stack();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c b/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c
new file mode 100644
index 000000000000..6deb8d560ddd
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/uretprobe_stack.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+
+#include <test_progs.h>
+#include "uretprobe_stack.skel.h"
+#include "../sdt.h"
+
+/* We set up target_1() -> target_2() -> target_3() -> target_4() -> USDT()
+ * call chain, each being traced by our BPF program. On entry or return from
+ * each target_*() we are capturing user stack trace and recording it in
+ * global variable, so that user space part of the test can validate it.
+ *
+ * Note, we put each target function into a custom section to get those
+ * __start_XXX/__stop_XXX symbols, generated by linker for us, which allow us
+ * to know address range of those functions
+ */
+__attribute__((section("uprobe__target_4")))
+__weak int target_4(void)
+{
+	STAP_PROBE1(uretprobe_stack, target, 42);
+	return 42;
+}
+
+extern const void *__start_uprobe__target_4;
+extern const void *__stop_uprobe__target_4;
+
+__attribute__((section("uprobe__target_3")))
+__weak int target_3(void)
+{
+	return target_4();
+}
+
+extern const void *__start_uprobe__target_3;
+extern const void *__stop_uprobe__target_3;
+
+__attribute__((section("uprobe__target_2")))
+__weak int target_2(void)
+{
+	return target_3();
+}
+
+extern const void *__start_uprobe__target_2;
+extern const void *__stop_uprobe__target_2;
+
+__attribute__((section("uprobe__target_1")))
+__weak int target_1(int depth)
+{
+	if (depth < 1)
+		return 1 + target_1(depth + 1);
+	else
+		return target_2();
+}
+
+extern const void *__start_uprobe__target_1;
+extern const void *__stop_uprobe__target_1;
+
+extern const void *__start_uretprobe_stack_sec;
+extern const void *__stop_uretprobe_stack_sec;
+
+struct range {
+	long start;
+	long stop;
+};
+
+static struct range targets[] = {
+	{}, /* we want target_1 to map to target[1], so need 1-based indexing */
+	{ (long)&__start_uprobe__target_1, (long)&__stop_uprobe__target_1 },
+	{ (long)&__start_uprobe__target_2, (long)&__stop_uprobe__target_2 },
+	{ (long)&__start_uprobe__target_3, (long)&__stop_uprobe__target_3 },
+	{ (long)&__start_uprobe__target_4, (long)&__stop_uprobe__target_4 },
+};
+
+static struct range caller = {
+	(long)&__start_uretprobe_stack_sec,
+	(long)&__stop_uretprobe_stack_sec,
+};
+
+static void validate_stack(__u64 *ips, int stack_len, int cnt, ...)
+{
+	int i, j;
+	va_list args;
+
+	if (!ASSERT_GT(stack_len, 0, "stack_len"))
+		return;
+
+	stack_len /= 8;
+
+	/* check if we have enough entries to satisfy test expectations */
+	if (!ASSERT_GE(stack_len, cnt, "stack_len2"))
+		return;
+
+	if (env.verbosity >= VERBOSE_NORMAL) {
+		printf("caller: %#lx - %#lx\n", caller.start, caller.stop);
+		for (i = 1; i < ARRAY_SIZE(targets); i++)
+			printf("target_%d: %#lx - %#lx\n", i, targets[i].start, targets[i].stop);
+		for (i = 0; i < stack_len; i++) {
+			for (j = 1; j < ARRAY_SIZE(targets); j++) {
+				if (ips[i] >= targets[j].start && ips[i] < targets[j].stop)
+					break;
+			}
+			if (j < ARRAY_SIZE(targets)) { /* found target match */
+				printf("ENTRY #%d: %#lx (in target_%d)\n", i, (long)ips[i], j);
+			} else if (ips[i] >= caller.start && ips[i] < caller.stop) {
+				printf("ENTRY #%d: %#lx (in caller)\n", i, (long)ips[i]);
+			} else {
+				printf("ENTRY #%d: %#lx\n", i, (long)ips[i]);
+			}
+		}
+	}
+
+	va_start(args, cnt);
+
+	for (i = cnt - 1; i >= 0; i--) {
+		/* most recent entry is the deepest target function */
+		const struct range *t = va_arg(args, const struct range *);
+
+		ASSERT_GE(ips[i], t->start, "addr_start");
+		ASSERT_LT(ips[i], t->stop, "addr_stop");
+	}
+
+	va_end(args);
+}
+
+/* __weak prevents inlining */
+__attribute__((section("uretprobe_stack_sec")))
+__weak void test_uretprobe_stack(void)
+{
+	LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
+	struct uretprobe_stack *skel;
+	int err;
+
+	skel = uretprobe_stack__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	err = uretprobe_stack__attach(skel);
+	if (!ASSERT_OK(err, "skel_attach"))
+		goto cleanup;
+
+	/* trigger */
+	ASSERT_EQ(target_1(0), 42 + 1, "trigger_return");
+
+	/*
+	 * Stacks captured on ENTRY uprobes
+	 */
+
+	/* (uprobe 1) target_1 in stack trace*/
+	validate_stack(skel->bss->entry_stack1, skel->bss->entry1_len,
+		       2, &caller, &targets[1]);
+	/* (uprobe 1, recursed) */
+	validate_stack(skel->bss->entry_stack1_recur, skel->bss->entry1_recur_len,
+		       3, &caller, &targets[1], &targets[1]);
+	/* (uprobe 2) caller -> target_1 -> target_1 -> target_2 */
+	validate_stack(skel->bss->entry_stack2, skel->bss->entry2_len,
+		       4, &caller, &targets[1], &targets[1], &targets[2]);
+	/* (uprobe 3) */
+	validate_stack(skel->bss->entry_stack3, skel->bss->entry3_len,
+		       5, &caller, &targets[1], &targets[1], &targets[2], &targets[3]);
+	/* (uprobe 4) caller -> target_1 -> target_1 -> target_2 -> target_3 -> target_4 */
+	validate_stack(skel->bss->entry_stack4, skel->bss->entry4_len,
+		       6, &caller, &targets[1], &targets[1], &targets[2], &targets[3], &targets[4]);
+
+	/* (USDT): full caller -> target_1 -> target_1 -> target_2 (uretprobed)
+	 *              -> target_3 -> target_4 (uretprobes) chain
+	 */
+	validate_stack(skel->bss->usdt_stack, skel->bss->usdt_len,
+		       6, &caller, &targets[1], &targets[1], &targets[2], &targets[3], &targets[4]);
+
+	/*
+	 * Now stacks captured on the way out in EXIT uprobes
+	 */
+
+	/* (uretprobe 4) everything up to target_4, but excluding it */
+	validate_stack(skel->bss->exit_stack4, skel->bss->exit4_len,
+		       5, &caller, &targets[1], &targets[1], &targets[2], &targets[3]);
+	/* we didn't install uretprobes on target_2 and target_3 */
+	/* (uretprobe 1, recur) first target_1 call only */
+	validate_stack(skel->bss->exit_stack1_recur, skel->bss->exit1_recur_len,
+		       2, &caller, &targets[1]);
+	/* (uretprobe 1) just a caller in the stack trace */
+	validate_stack(skel->bss->exit_stack1, skel->bss->exit1_len,
+		       1, &caller);
+
+cleanup:
+	uretprobe_stack__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall.c b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
new file mode 100644
index 000000000000..8a4fa6c7ef59
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+SEC("uretprobe//proc/self/exe:uretprobe_regs_trigger")
+int uretprobe(struct pt_regs *ctx)
+{
+	__builtin_memcpy(&regs, ctx, sizeof(regs));
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
new file mode 100644
index 000000000000..0d7f1a7db2e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uprobe_syscall_executed.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <string.h>
+
+struct pt_regs regs;
+
+char _license[] SEC("license") = "GPL";
+
+int executed = 0;
+
+SEC("uretprobe.multi")
+int test(struct pt_regs *regs)
+{
+	executed = 1;
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/progs/uretprobe_stack.c b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
new file mode 100644
index 000000000000..9fdcf396b8f4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/uretprobe_stack.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include <bpf/usdt.bpf.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 entry_stack1[32], exit_stack1[32];
+__u64 entry_stack1_recur[32], exit_stack1_recur[32];
+__u64 entry_stack2[32];
+__u64 entry_stack3[32];
+__u64 entry_stack4[32], exit_stack4[32];
+__u64 usdt_stack[32];
+
+int entry1_len, exit1_len;
+int entry1_recur_len, exit1_recur_len;
+int entry2_len, exit2_len;
+int entry3_len, exit3_len;
+int entry4_len, exit4_len;
+int usdt_len;
+
+#define SZ sizeof(usdt_stack)
+
+SEC("uprobe//proc/self/exe:target_1")
+int BPF_UPROBE(uprobe_1)
+{
+	/* target_1 is recursive wit depth of 2, so we capture two separate
+	 * stack traces, depending on which occurence it is
+	 */
+	static bool recur = false;
+
+	if (!recur)
+		entry1_len = bpf_get_stack(ctx, &entry_stack1, SZ, BPF_F_USER_STACK);
+	else
+		entry1_recur_len = bpf_get_stack(ctx, &entry_stack1_recur, SZ, BPF_F_USER_STACK);
+
+	recur = true;
+	return 0;
+}
+
+SEC("uretprobe//proc/self/exe:target_1")
+int BPF_URETPROBE(uretprobe_1)
+{
+	/* see above, target_1 is recursive */
+	static bool recur = false;
+
+	/* NOTE: order of returns is reversed to order of entries */
+	if (!recur)
+		exit1_recur_len = bpf_get_stack(ctx, &exit_stack1_recur, SZ, BPF_F_USER_STACK);
+	else
+		exit1_len = bpf_get_stack(ctx, &exit_stack1, SZ, BPF_F_USER_STACK);
+
+	recur = true;
+	return 0;
+}
+
+SEC("uprobe//proc/self/exe:target_2")
+int BPF_UPROBE(uprobe_2)
+{
+	entry2_len = bpf_get_stack(ctx, &entry_stack2, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+/* no uretprobe for target_2 */
+
+SEC("uprobe//proc/self/exe:target_3")
+int BPF_UPROBE(uprobe_3)
+{
+	entry3_len = bpf_get_stack(ctx, &entry_stack3, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+/* no uretprobe for target_3 */
+
+SEC("uprobe//proc/self/exe:target_4")
+int BPF_UPROBE(uprobe_4)
+{
+	entry4_len = bpf_get_stack(ctx, &entry_stack4, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+SEC("uretprobe//proc/self/exe:target_4")
+int BPF_URETPROBE(uretprobe_4)
+{
+	exit4_len = bpf_get_stack(ctx, &exit_stack4, SZ, BPF_F_USER_STACK);
+	return 0;
+}
+
+SEC("usdt//proc/self/exe:uretprobe_stack:target")
+int BPF_USDT(usdt_probe)
+{
+	usdt_len = bpf_get_stack(ctx, &usdt_stack, SZ, BPF_F_USER_STACK);
+	return 0;
+}
diff --git a/tools/testing/selftests/x86/test_shadow_stack.c b/tools/testing/selftests/x86/test_shadow_stack.c
index ee909a7927f9..21af54d5f4ea 100644
--- a/tools/testing/selftests/x86/test_shadow_stack.c
+++ b/tools/testing/selftests/x86/test_shadow_stack.c
@@ -34,6 +34,7 @@
 #include <sys/ptrace.h>
 #include <sys/signal.h>
 #include <linux/elf.h>
+#include <linux/perf_event.h>
 
 /*
  * Define the ABI defines if needed, so people can run the tests
@@ -734,6 +735,144 @@ int test_32bit(void)
 	return !segv_triggered;
 }
 
+static int parse_uint_from_file(const char *file, const char *fmt)
+{
+	int err, ret;
+	FILE *f;
+
+	f = fopen(file, "re");
+	if (!f) {
+		err = -errno;
+		printf("failed to open '%s': %d\n", file, err);
+		return err;
+	}
+	err = fscanf(f, fmt, &ret);
+	if (err != 1) {
+		err = err == EOF ? -EIO : -errno;
+		printf("failed to parse '%s': %d\n", file, err);
+		fclose(f);
+		return err;
+	}
+	fclose(f);
+	return ret;
+}
+
+static int determine_uprobe_perf_type(void)
+{
+	const char *file = "/sys/bus/event_source/devices/uprobe/type";
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int determine_uprobe_retprobe_bit(void)
+{
+	const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe";
+
+	return parse_uint_from_file(file, "config:%d\n");
+}
+
+static ssize_t get_uprobe_offset(const void *addr)
+{
+	size_t start, end, base;
+	char buf[256];
+	bool found = false;
+	FILE *f;
+
+	f = fopen("/proc/self/maps", "r");
+	if (!f)
+		return -errno;
+
+	while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) {
+		if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) {
+			found = true;
+			break;
+		}
+	}
+
+	fclose(f);
+
+	if (!found)
+		return -ESRCH;
+
+	return (uintptr_t)addr - start + base;
+}
+
+static __attribute__((noinline)) void uretprobe_trigger(void)
+{
+	asm volatile ("");
+}
+
+/*
+ * This test setups return uprobe, which is sensitive to shadow stack
+ * (crashes without extra fix). After executing the uretprobe we fail
+ * the test if we receive SIGSEGV, no crash means we're good.
+ *
+ * Helper functions above borrowed from bpf selftests.
+ */
+static int test_uretprobe(void)
+{
+	const size_t attr_sz = sizeof(struct perf_event_attr);
+	const char *file = "/proc/self/exe";
+	int bit, fd = 0, type, err = 1;
+	struct perf_event_attr attr;
+	struct sigaction sa = {};
+	ssize_t offset;
+
+	type = determine_uprobe_perf_type();
+	if (type < 0) {
+		if (type == -ENOENT)
+			printf("[SKIP]\tUretprobe test, uprobes are not available\n");
+		return 0;
+	}
+
+	offset = get_uprobe_offset(uretprobe_trigger);
+	if (offset < 0)
+		return 1;
+
+	bit = determine_uprobe_retprobe_bit();
+	if (bit < 0)
+		return 1;
+
+	sa.sa_sigaction = segv_gp_handler;
+	sa.sa_flags = SA_SIGINFO;
+	if (sigaction(SIGSEGV, &sa, NULL))
+		return 1;
+
+	/* Setup return uprobe through perf event interface. */
+	memset(&attr, 0, attr_sz);
+	attr.size = attr_sz;
+	attr.type = type;
+	attr.config = 1 << bit;
+	attr.config1 = (__u64) (unsigned long) file;
+	attr.config2 = offset;
+
+	fd = syscall(__NR_perf_event_open, &attr, 0 /* pid */, -1 /* cpu */,
+		     -1 /* group_fd */, PERF_FLAG_FD_CLOEXEC);
+	if (fd < 0)
+		goto out;
+
+	if (sigsetjmp(jmp_buffer, 1))
+		goto out;
+
+	ARCH_PRCTL(ARCH_SHSTK_ENABLE, ARCH_SHSTK_SHSTK);
+
+	/*
+	 * This either segfaults and goes through sigsetjmp above
+	 * or succeeds and we're good.
+	 */
+	uretprobe_trigger();
+
+	printf("[OK]\tUretprobe test\n");
+	err = 0;
+
+out:
+	ARCH_PRCTL(ARCH_SHSTK_DISABLE, ARCH_SHSTK_SHSTK);
+	signal(SIGSEGV, SIG_DFL);
+	if (fd)
+		close(fd);
+	return err;
+}
+
 void segv_handler_ptrace(int signum, siginfo_t *si, void *uc)
 {
 	/* The SSP adjustment caused a segfault. */
@@ -926,6 +1065,12 @@ int main(int argc, char *argv[])
 		goto out;
 	}
 
+	if (test_uretprobe()) {
+		ret = 1;
+		printf("[FAIL]\turetprobe test\n");
+		goto out;
+	}
+
 	return ret;
 
 out: