diff --git a/MAINTAINERS b/MAINTAINERS
index 11ab51646d96..655ea596b597 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23367,6 +23367,19 @@ F:	drivers/mtd/ubi/
 F:	include/linux/mtd/ubi.h
 F:	include/uapi/mtd/ubi-user.h
 
+UPROBES
+M:	Masami Hiramatsu <mhiramat@kernel.org>
+M:	Oleg Nesterov <oleg@redhat.com>
+M:	Peter Zijlstra <peterz@infradead.org>
+L:	linux-kernel@vger.kernel.org
+L:	linux-trace-kernel@vger.kernel.org
+S:	Maintained
+F:	arch/*/include/asm/uprobes.h
+F:	arch/*/kernel/probes/uprobes.c
+F:	arch/*/kernel/uprobes.c
+F:	include/linux/uprobes.h
+F:	kernel/events/uprobes.c
+
 USB "USBNET" DRIVER FRAMEWORK
 M:	Oliver Neukum <oneukum@suse.com>
 L:	netdev@vger.kernel.org
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index 097e5a18db52..83073fa3c989 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -385,6 +385,7 @@
 460	common	lsm_set_self_attr	sys_lsm_set_self_attr
 461	common	lsm_list_modules	sys_lsm_list_modules
 462 	common  mseal			sys_mseal
+467	common	uretprobe		sys_uretprobe
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
index 42fee8959df7..4cb77e004615 100644
--- a/arch/x86/include/asm/shstk.h
+++ b/arch/x86/include/asm/shstk.h
@@ -21,6 +21,8 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
 void shstk_free(struct task_struct *p);
 int setup_signal_shadow_stack(struct ksignal *ksig);
 int restore_signal_shadow_stack(void);
+int shstk_update_last_frame(unsigned long val);
+bool shstk_is_enabled(void);
 #else
 static inline long shstk_prctl(struct task_struct *task, int option,
 			       unsigned long arg2) { return -EINVAL; }
@@ -31,6 +33,8 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
 static inline void shstk_free(struct task_struct *p) {}
 static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
 static inline int restore_signal_shadow_stack(void) { return 0; }
+static inline int shstk_update_last_frame(unsigned long val) { return 0; }
+static inline bool shstk_is_enabled(void) { return false; }
 #endif /* CONFIG_X86_USER_SHADOW_STACK */
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 6f1e9883f074..059685612362 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -577,3 +577,19 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
 		return wrss_control(true);
 	return -EINVAL;
 }
+
+int shstk_update_last_frame(unsigned long val)
+{
+	unsigned long ssp;
+
+	if (!features_enabled(ARCH_SHSTK_SHSTK))
+		return 0;
+
+	ssp = get_user_shstk_addr();
+	return write_user_shstk_64((u64 __user *)ssp, (u64)val);
+}
+
+bool shstk_is_enabled(void)
+{
+	return features_enabled(ARCH_SHSTK_SHSTK);
+}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 6c07f6daaa22..5a952c5ea66b 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -12,6 +12,7 @@
 #include <linux/ptrace.h>
 #include <linux/uprobes.h>
 #include <linux/uaccess.h>
+#include <linux/syscalls.h>
 
 #include <linux/kdebug.h>
 #include <asm/processor.h>
@@ -308,6 +309,122 @@ static int uprobe_init_insn(struct arch_uprobe *auprobe, struct insn *insn, bool
 }
 
 #ifdef CONFIG_X86_64
+
+asm (
+	".pushsection .rodata\n"
+	".global uretprobe_trampoline_entry\n"
+	"uretprobe_trampoline_entry:\n"
+	"pushq %rax\n"
+	"pushq %rcx\n"
+	"pushq %r11\n"
+	"movq $" __stringify(__NR_uretprobe) ", %rax\n"
+	"syscall\n"
+	".global uretprobe_syscall_check\n"
+	"uretprobe_syscall_check:\n"
+	"popq %r11\n"
+	"popq %rcx\n"
+
+	/* The uretprobe syscall replaces stored %rax value with final
+	 * return address, so we don't restore %rax in here and just
+	 * call ret.
+	 */
+	"retq\n"
+	".global uretprobe_trampoline_end\n"
+	"uretprobe_trampoline_end:\n"
+	".popsection\n"
+);
+
+extern u8 uretprobe_trampoline_entry[];
+extern u8 uretprobe_trampoline_end[];
+extern u8 uretprobe_syscall_check[];
+
+void *arch_uprobe_trampoline(unsigned long *psize)
+{
+	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+	struct pt_regs *regs = task_pt_regs(current);
+
+	/*
+	 * At the moment the uretprobe syscall trampoline is supported
+	 * only for native 64-bit process, the compat process still uses
+	 * standard breakpoint.
+	 */
+	if (user_64bit_mode(regs)) {
+		*psize = uretprobe_trampoline_end - uretprobe_trampoline_entry;
+		return uretprobe_trampoline_entry;
+	}
+
+	*psize = UPROBE_SWBP_INSN_SIZE;
+	return &insn;
+}
+
+static unsigned long trampoline_check_ip(void)
+{
+	unsigned long tramp = uprobe_get_trampoline_vaddr();
+
+	return tramp + (uretprobe_syscall_check - uretprobe_trampoline_entry);
+}
+
+SYSCALL_DEFINE0(uretprobe)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	unsigned long err, ip, sp, r11_cx_ax[3];
+
+	if (regs->ip != trampoline_check_ip())
+		goto sigill;
+
+	err = copy_from_user(r11_cx_ax, (void __user *)regs->sp, sizeof(r11_cx_ax));
+	if (err)
+		goto sigill;
+
+	/* expose the "right" values of r11/cx/ax/sp to uprobe_consumer/s */
+	regs->r11 = r11_cx_ax[0];
+	regs->cx  = r11_cx_ax[1];
+	regs->ax  = r11_cx_ax[2];
+	regs->sp += sizeof(r11_cx_ax);
+	regs->orig_ax = -1;
+
+	ip = regs->ip;
+	sp = regs->sp;
+
+	uprobe_handle_trampoline(regs);
+
+	/*
+	 * Some of the uprobe consumers has changed sp, we can do nothing,
+	 * just return via iret.
+	 * .. or shadow stack is enabled, in which case we need to skip
+	 * return through the user space stack address.
+	 */
+	if (regs->sp != sp || shstk_is_enabled())
+		return regs->ax;
+	regs->sp -= sizeof(r11_cx_ax);
+
+	/* for the case uprobe_consumer has changed r11/cx */
+	r11_cx_ax[0] = regs->r11;
+	r11_cx_ax[1] = regs->cx;
+
+	/*
+	 * ax register is passed through as return value, so we can use
+	 * its space on stack for ip value and jump to it through the
+	 * trampoline's ret instruction
+	 */
+	r11_cx_ax[2] = regs->ip;
+	regs->ip = ip;
+
+	err = copy_to_user((void __user *)regs->sp, r11_cx_ax, sizeof(r11_cx_ax));
+	if (err)
+		goto sigill;
+
+	/* ensure sysret, see do_syscall_64() */
+	regs->r11 = regs->flags;
+	regs->cx  = regs->ip;
+
+	return regs->ax;
+
+sigill:
+	force_sig(SIGILL);
+	return -1;
+}
+
 /*
  * If arch_uprobe->insn doesn't use rip-relative addressing, return
  * immediately.  Otherwise, rewrite the instruction so that it accesses
@@ -1076,8 +1193,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
 		return orig_ret_vaddr;
 
 	nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
-	if (likely(!nleft))
+	if (likely(!nleft)) {
+		if (shstk_update_last_frame(trampoline_vaddr)) {
+			force_sig(SIGSEGV);
+			return -1;
+		}
 		return orig_ret_vaddr;
+	}
 
 	if (nleft != rasize) {
 		pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index fff820c3e93e..4bcf6754738d 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -979,6 +979,8 @@ asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flag
 /* x86 */
 asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int on);
 
+asmlinkage long sys_uretprobe(void);
+
 /* pciconfig: alpha, arm, arm64, ia64, sparc */
 asmlinkage long sys_pciconfig_read(unsigned long bus, unsigned long dfn,
 				unsigned long off, unsigned long len,
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index f46e0ca0169c..b503fafb7fb3 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -138,6 +138,9 @@ extern bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check c
 extern bool arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs);
 extern void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
 					 void *src, unsigned long len);
+extern void uprobe_handle_trampoline(struct pt_regs *regs);
+extern void *arch_uprobe_trampoline(unsigned long *psize);
+extern unsigned long uprobe_get_trampoline_vaddr(void);
 #else /* !CONFIG_UPROBES */
 struct uprobes_state {
 };
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 5bf6148cac2b..985a262d0f9e 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -841,8 +841,11 @@ __SYSCALL(__NR_lsm_list_modules, sys_lsm_list_modules)
 #define __NR_mseal 462
 __SYSCALL(__NR_mseal, sys_mseal)
 
+#define __NR_uretprobe 463
+__SYSCALL(__NR_uretprobe, sys_uretprobe)
+
 #undef __NR_syscalls
-#define __NR_syscalls 463
+#define __NR_syscalls 464
 
 /*
  * 32 bit systems traditionally used different
diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index ad57944b6c40..8d57255e5b29 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -11,6 +11,7 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <linux/sched/task_stack.h>
+#include <linux/uprobes.h>
 
 #include "internal.h"
 
@@ -176,13 +177,51 @@ put_callchain_entry(int rctx)
 	put_recursion_context(this_cpu_ptr(callchain_recursion), rctx);
 }
 
+static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entry,
+					       int start_entry_idx)
+{
+#ifdef CONFIG_UPROBES
+	struct uprobe_task *utask = current->utask;
+	struct return_instance *ri;
+	__u64 *cur_ip, *last_ip, tramp_addr;
+
+	if (likely(!utask || !utask->return_instances))
+		return;
+
+	cur_ip = &entry->ip[start_entry_idx];
+	last_ip = &entry->ip[entry->nr - 1];
+	ri = utask->return_instances;
+	tramp_addr = uprobe_get_trampoline_vaddr();
+
+	/*
+	 * If there are pending uretprobes for the current thread, they are
+	 * recorded in a list inside utask->return_instances; each such
+	 * pending uretprobe replaces traced user function's return address on
+	 * the stack, so when stack trace is captured, instead of seeing
+	 * actual function's return address, we'll have one or many uretprobe
+	 * trampoline addresses in the stack trace, which are not helpful and
+	 * misleading to users.
+	 * So here we go over the pending list of uretprobes, and each
+	 * encountered trampoline address is replaced with actual return
+	 * address.
+	 */
+	while (ri && cur_ip <= last_ip) {
+		if (*cur_ip == tramp_addr) {
+			*cur_ip = ri->orig_ret_vaddr;
+			ri = ri->next;
+		}
+		cur_ip++;
+	}
+#endif
+}
+
 struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 		   u32 max_stack, bool crosstask, bool add_mark)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
-	int rctx;
+	int rctx, start_entry_idx;
 
 	entry = get_callchain_entry(&rctx);
 	if (!entry)
@@ -215,7 +254,9 @@ get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user,
 			if (add_mark)
 				perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
+			start_entry_idx = entry->nr;
 			perf_callchain_user(&ctx, regs);
+			fixup_uretprobe_trampoline_entries(entry, start_entry_idx);
 		}
 	}
 
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2c83ba776fc7..99be2adedbc0 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -1474,11 +1474,20 @@ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area)
 	return ret;
 }
 
+void * __weak arch_uprobe_trampoline(unsigned long *psize)
+{
+	static uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+
+	*psize = UPROBE_SWBP_INSN_SIZE;
+	return &insn;
+}
+
 static struct xol_area *__create_xol_area(unsigned long vaddr)
 {
 	struct mm_struct *mm = current->mm;
-	uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+	unsigned long insns_size;
 	struct xol_area *area;
+	void *insns;
 
 	area = kmalloc(sizeof(*area), GFP_KERNEL);
 	if (unlikely(!area))
@@ -1502,7 +1511,8 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
 	/* Reserve the 1st slot for get_trampoline_vaddr() */
 	set_bit(0, area->bitmap);
 	atomic_set(&area->slot_count, 1);
-	arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE);
+	insns = arch_uprobe_trampoline(&insns_size);
+	arch_uprobe_copy_ixol(area->pages[0], 0, insns, insns_size);
 
 	if (!xol_add_vma(mm, area))
 		return area;
@@ -1827,7 +1837,7 @@ void uprobe_copy_process(struct task_struct *t, unsigned long flags)
  *
  * Returns -1 in case the xol_area is not allocated.
  */
-static unsigned long get_trampoline_vaddr(void)
+unsigned long uprobe_get_trampoline_vaddr(void)
 {
 	struct xol_area *area;
 	unsigned long trampoline_vaddr = -1;
@@ -1878,7 +1888,7 @@ static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs)
 	if (!ri)
 		return;
 
-	trampoline_vaddr = get_trampoline_vaddr();
+	trampoline_vaddr = uprobe_get_trampoline_vaddr();
 	orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs);
 	if (orig_ret_vaddr == -1)
 		goto fail;
@@ -2123,7 +2133,7 @@ static struct return_instance *find_next_ret_chain(struct return_instance *ri)
 	return ri;
 }
 
-static void handle_trampoline(struct pt_regs *regs)
+void uprobe_handle_trampoline(struct pt_regs *regs)
 {
 	struct uprobe_task *utask;
 	struct return_instance *ri, *next;
@@ -2149,6 +2159,15 @@ static void handle_trampoline(struct pt_regs *regs)
 
 		instruction_pointer_set(regs, ri->orig_ret_vaddr);
 		do {
+			/* pop current instance from the stack of pending return instances,
+			 * as it's not pending anymore: we just fixed up original
+			 * instruction pointer in regs and are about to call handlers;
+			 * this allows fixup_uretprobe_trampoline_entries() to properly fix up
+			 * captured stack traces from uretprobe handlers, in which pending
+			 * trampoline addresses on the stack are replaced with correct
+			 * original return addresses
+			 */
+			utask->return_instances = ri->next;
 			if (valid)
 				handle_uretprobe_chain(ri, regs);
 			ri = free_ret_instance(ri);
@@ -2187,8 +2206,8 @@ static void handle_swbp(struct pt_regs *regs)
 	int is_swbp;
 
 	bp_vaddr = uprobe_get_swbp_addr(regs);
-	if (bp_vaddr == get_trampoline_vaddr())
-		return handle_trampoline(regs);
+	if (bp_vaddr == uprobe_get_trampoline_vaddr())
+		return uprobe_handle_trampoline(regs);
 
 	uprobe = find_active_uprobe(bp_vaddr, &is_swbp);
 	if (!uprobe) {
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index 2ef820a2d067..c00a86931f8c 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -390,3 +390,5 @@ COND_SYSCALL(setuid16);
 
 /* restartable sequence */
 COND_SYSCALL(rseq);
+
+COND_SYSCALL(uretprobe);
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 16383247bdbf..61a6da808203 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -678,6 +678,21 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
 }
 
 #ifdef CONFIG_MODULES
+static int validate_module_probe_symbol(const char *modname, const char *symbol);
+
+static int register_module_trace_kprobe(struct module *mod, struct trace_kprobe *tk)
+{
+	const char *p;
+	int ret = 0;
+
+	p = strchr(trace_kprobe_symbol(tk), ':');
+	if (p)
+		ret = validate_module_probe_symbol(module_name(mod), p + 1);
+	if (!ret)
+		ret = __register_trace_kprobe(tk);
+	return ret;
+}
+
 /* Module notifier call back, checking event on the module */
 static int trace_kprobe_module_callback(struct notifier_block *nb,
 				       unsigned long val, void *data)
@@ -696,7 +711,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
 		if (trace_kprobe_within_module(tk, mod)) {
 			/* Don't need to check busy - this should have gone. */
 			__unregister_trace_kprobe(tk);
-			ret = __register_trace_kprobe(tk);
+			ret = register_module_trace_kprobe(mod, tk);
 			if (ret)
 				pr_warn("Failed to re-register probe %s on %s: %d\n",
 					trace_probe_name(&tk->tp),
@@ -747,17 +762,81 @@ static int count_mod_symbols(void *data, const char *name, unsigned long unused)
 	return 0;
 }
 
-static unsigned int number_of_same_symbols(char *func_name)
+static unsigned int number_of_same_symbols(const char *mod, const char *func_name)
 {
 	struct sym_count_ctx ctx = { .count = 0, .name = func_name };
 
-	kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
+	if (!mod)
+		kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
 
-	module_kallsyms_on_each_symbol(NULL, count_mod_symbols, &ctx);
+	module_kallsyms_on_each_symbol(mod, count_mod_symbols, &ctx);
 
 	return ctx.count;
 }
 
+static int validate_module_probe_symbol(const char *modname, const char *symbol)
+{
+	unsigned int count = number_of_same_symbols(modname, symbol);
+
+	if (count > 1) {
+		/*
+		 * Users should use ADDR to remove the ambiguity of
+		 * using KSYM only.
+		 */
+		return -EADDRNOTAVAIL;
+	} else if (count == 0) {
+		/*
+		 * We can return ENOENT earlier than when register the
+		 * kprobe.
+		 */
+		return -ENOENT;
+	}
+	return 0;
+}
+
+#ifdef CONFIG_MODULES
+/* Return NULL if the module is not loaded or under unloading. */
+static struct module *try_module_get_by_name(const char *name)
+{
+	struct module *mod;
+
+	rcu_read_lock_sched();
+	mod = find_module(name);
+	if (mod && !try_module_get(mod))
+		mod = NULL;
+	rcu_read_unlock_sched();
+
+	return mod;
+}
+#else
+#define try_module_get_by_name(name)	(NULL)
+#endif
+
+static int validate_probe_symbol(char *symbol)
+{
+	struct module *mod = NULL;
+	char *modname = NULL, *p;
+	int ret = 0;
+
+	p = strchr(symbol, ':');
+	if (p) {
+		modname = symbol;
+		symbol = p + 1;
+		*p = '\0';
+		mod = try_module_get_by_name(modname);
+		if (!mod)
+			goto out;
+	}
+
+	ret = validate_module_probe_symbol(modname, symbol);
+out:
+	if (p)
+		*p = ':';
+	if (mod)
+		module_put(mod);
+	return ret;
+}
+
 static int trace_kprobe_entry_handler(struct kretprobe_instance *ri,
 				      struct pt_regs *regs);
 
@@ -881,6 +960,14 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 			trace_probe_log_err(0, BAD_PROBE_ADDR);
 			goto parse_error;
 		}
+		ret = validate_probe_symbol(symbol);
+		if (ret) {
+			if (ret == -EADDRNOTAVAIL)
+				trace_probe_log_err(0, NON_UNIQ_SYMBOL);
+			else
+				trace_probe_log_err(0, BAD_PROBE_ADDR);
+			goto parse_error;
+		}
 		if (is_return)
 			ctx.flags |= TPARG_FL_RETURN;
 		ret = kprobe_on_func_entry(NULL, symbol, offset);
@@ -893,31 +980,6 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		}
 	}
 
-	if (symbol && !strchr(symbol, ':')) {
-		unsigned int count;
-
-		count = number_of_same_symbols(symbol);
-		if (count > 1) {
-			/*
-			 * Users should use ADDR to remove the ambiguity of
-			 * using KSYM only.
-			 */
-			trace_probe_log_err(0, NON_UNIQ_SYMBOL);
-			ret = -EADDRNOTAVAIL;
-
-			goto error;
-		} else if (count == 0) {
-			/*
-			 * We can return ENOENT earlier than when register the
-			 * kprobe.
-			 */
-			trace_probe_log_err(0, BAD_PROBE_ADDR);
-			ret = -ENOENT;
-
-			goto error;
-		}
-	}
-
 	trace_probe_log_set_index(0);
 	if (event) {
 		ret = traceprobe_parse_event_name(&event, &group, gbuf,
@@ -1835,21 +1897,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
 	char *event;
 
 	if (func) {
-		unsigned int count;
-
-		count = number_of_same_symbols(func);
-		if (count > 1)
-			/*
-			 * Users should use addr to remove the ambiguity of
-			 * using func only.
-			 */
-			return ERR_PTR(-EADDRNOTAVAIL);
-		else if (count == 0)
-			/*
-			 * We can return ENOENT earlier than when register the
-			 * kprobe.
-			 */
-			return ERR_PTR(-ENOENT);
+		ret = validate_probe_symbol(func);
+		if (ret)
+			return ERR_PTR(ret);
 	}
 
 	/*
@@ -2023,19 +2073,16 @@ static __init int kprobe_trace_self_tests_init(void)
 	pr_info("Testing kprobe tracing: ");
 
 	ret = create_or_delete_trace_kprobe("p:testprobe kprobe_trace_selftest_target $stack $stack0 +0($stack)");
-	if (WARN_ON_ONCE(ret)) {
-		pr_warn("error on probing function entry.\n");
+	if (WARN_ONCE(ret, "error on probing function entry.")) {
 		warn++;
 	} else {
 		/* Enable trace point */
 		tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
-		if (WARN_ON_ONCE(tk == NULL)) {
-			pr_warn("error on getting new probe.\n");
+		if (WARN_ONCE(tk == NULL, "error on probing function entry.")) {
 			warn++;
 		} else {
 			file = find_trace_probe_file(tk, top_trace_array());
-			if (WARN_ON_ONCE(file == NULL)) {
-				pr_warn("error on getting probe file.\n");
+			if (WARN_ONCE(file == NULL, "error on getting probe file.")) {
 				warn++;
 			} else
 				enable_trace_kprobe(
@@ -2044,19 +2091,16 @@ static __init int kprobe_trace_self_tests_init(void)
 	}
 
 	ret = create_or_delete_trace_kprobe("r:testprobe2 kprobe_trace_selftest_target $retval");
-	if (WARN_ON_ONCE(ret)) {
-		pr_warn("error on probing function return.\n");
+	if (WARN_ONCE(ret, "error on probing function return.")) {
 		warn++;
 	} else {
 		/* Enable trace point */
 		tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
-		if (WARN_ON_ONCE(tk == NULL)) {
-			pr_warn("error on getting 2nd new probe.\n");
+		if (WARN_ONCE(tk == NULL, "error on getting 2nd new probe.")) {
 			warn++;
 		} else {
 			file = find_trace_probe_file(tk, top_trace_array());
-			if (WARN_ON_ONCE(file == NULL)) {
-				pr_warn("error on getting probe file.\n");
+			if (WARN_ONCE(file == NULL, "error on getting probe file.")) {
 				warn++;
 			} else
 				enable_trace_kprobe(
@@ -2079,18 +2123,15 @@ static __init int kprobe_trace_self_tests_init(void)
 
 	/* Disable trace points before removing it */
 	tk = find_trace_kprobe("testprobe", KPROBE_EVENT_SYSTEM);
-	if (WARN_ON_ONCE(tk == NULL)) {
-		pr_warn("error on getting test probe.\n");
+	if (WARN_ONCE(tk == NULL, "error on getting test probe.")) {
 		warn++;
 	} else {
-		if (trace_kprobe_nhit(tk) != 1) {
-			pr_warn("incorrect number of testprobe hits\n");
+		if (WARN_ONCE(trace_kprobe_nhit(tk) != 1,
+				 "incorrect number of testprobe hits."))
 			warn++;
-		}
 
 		file = find_trace_probe_file(tk, top_trace_array());
-		if (WARN_ON_ONCE(file == NULL)) {
-			pr_warn("error on getting probe file.\n");
+		if (WARN_ONCE(file == NULL, "error on getting probe file.")) {
 			warn++;
 		} else
 			disable_trace_kprobe(
@@ -2098,18 +2139,15 @@ static __init int kprobe_trace_self_tests_init(void)
 	}
 
 	tk = find_trace_kprobe("testprobe2", KPROBE_EVENT_SYSTEM);
-	if (WARN_ON_ONCE(tk == NULL)) {
-		pr_warn("error on getting 2nd test probe.\n");
+	if (WARN_ONCE(tk == NULL, "error on getting 2nd test probe.")) {
 		warn++;
 	} else {
-		if (trace_kprobe_nhit(tk) != 1) {
-			pr_warn("incorrect number of testprobe2 hits\n");
+		if (WARN_ONCE(trace_kprobe_nhit(tk) != 1,
+				 "incorrect number of testprobe2 hits."))
 			warn++;
-		}
 
 		file = find_trace_probe_file(tk, top_trace_array());
-		if (WARN_ON_ONCE(file == NULL)) {
-			pr_warn("error on getting probe file.\n");
+		if (WARN_ONCE(file == NULL, "error on getting probe file.")) {
 			warn++;
 		} else
 			disable_trace_kprobe(
@@ -2117,23 +2155,15 @@ static __init int kprobe_trace_self_tests_init(void)
 	}
 
 	ret = create_or_delete_trace_kprobe("-:testprobe");
-	if (WARN_ON_ONCE(ret)) {
-		pr_warn("error on deleting a probe.\n");
+	if (WARN_ONCE(ret, "error on deleting a probe."))
 		warn++;
-	}
 
 	ret = create_or_delete_trace_kprobe("-:testprobe2");
-	if (WARN_ON_ONCE(ret)) {
-		pr_warn("error on deleting a probe.\n");
+	if (WARN_ONCE(ret, "error on deleting a probe."))
 		warn++;
-	}
+
 
 end:
-	ret = dyn_events_release_all(&trace_kprobe_ops);
-	if (WARN_ON_ONCE(ret)) {
-		pr_warn("error on cleaning up probes.\n");
-		warn++;
-	}
 	/*
 	 * Wait for the optimizer work to finish. Otherwise it might fiddle
 	 * with probes in already freed __init text.
diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c
index 64e715e7ed11..0a50b05add96 100644
--- a/samples/fprobe/fprobe_example.c
+++ b/samples/fprobe/fprobe_example.c
@@ -150,4 +150,5 @@ static void __exit fprobe_exit(void)
 
 module_init(fprobe_init)
 module_exit(fprobe_exit)
+MODULE_DESCRIPTION("sample kernel module showing the use of fprobe");
 MODULE_LICENSE("GPL");
diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c
index ef44c614c6d9..53ec6c8b8c40 100644
--- a/samples/kprobes/kprobe_example.c
+++ b/samples/kprobes/kprobe_example.c
@@ -125,4 +125,5 @@ static void __exit kprobe_exit(void)
 
 module_init(kprobe_init)
 module_exit(kprobe_exit)
+MODULE_DESCRIPTION("sample kernel module showing the use of kprobes");
 MODULE_LICENSE("GPL");
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index ed79fd3d48fb..65d6dcafd742 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -104,4 +104,5 @@ static void __exit kretprobe_exit(void)
 
 module_init(kretprobe_init)
 module_exit(kretprobe_exit)
+MODULE_DESCRIPTION("sample kernel module showing the use of return probes");
 MODULE_LICENSE("GPL");
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: