diff --git a/arch/arm64/kernel/kprobes-arm64.h b/arch/arm64/kernel/kprobes-arm64.h
index ff8a55f..0b9987d 100644
--- a/arch/arm64/kernel/kprobes-arm64.h
+++ b/arch/arm64/kernel/kprobes-arm64.h
@@ -27,4 +27,40 @@ extern kprobes_pstate_check_t * const kprobe_condition_checks[16];
 enum kprobe_insn __kprobes
 arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi);
 
+#define SAVE_REGS_STRING\
+	"	stp x0, x1, [sp, #16 * 0]\n"	\
+	"	stp x2, x3, [sp, #16 * 1]\n"	\
+	"	stp x4, x5, [sp, #16 * 2]\n"	\
+	"	stp x6, x7, [sp, #16 * 3]\n"	\
+	"	stp x8, x9, [sp, #16 * 4]\n"	\
+	"	stp x10, x11, [sp, #16 * 5]\n"	\
+	"	stp x12, x13, [sp, #16 * 6]\n"	\
+	"	stp x14, x15, [sp, #16 * 7]\n"	\
+	"	stp x16, x17, [sp, #16 * 8]\n"	\
+	"	stp x18, x19, [sp, #16 * 9]\n"	\
+	"	stp x20, x21, [sp, #16 * 10]\n"	\
+	"	stp x22, x23, [sp, #16 * 11]\n"	\
+	"	stp x24, x25, [sp, #16 * 12]\n"	\
+	"	stp x26, x27, [sp, #16 * 13]\n"	\
+	"	stp x28, x29, [sp, #16 * 14]\n"	\
+	"	str x30,   [sp, #16 * 15]\n"
+
+#define RESTORE_REGS_STRING\
+	"	ldp x2, x3, [sp, #16 * 1]\n"	\
+	"	ldp x4, x5, [sp, #16 * 2]\n"	\
+	"	ldp x6, x7, [sp, #16 * 3]\n"	\
+	"	ldp x8, x9, [sp, #16 * 4]\n"	\
+	"	ldp x10, x11, [sp, #16 * 5]\n"	\
+	"	ldp x12, x13, [sp, #16 * 6]\n"	\
+	"	ldp x14, x15, [sp, #16 * 7]\n"	\
+	"	ldp x16, x17, [sp, #16 * 8]\n"	\
+	"	ldp x18, x19, [sp, #16 * 9]\n"	\
+	"	ldp x20, x21, [sp, #16 * 10]\n"	\
+	"	ldp x22, x23, [sp, #16 * 11]\n"	\
+	"	ldp x24, x25, [sp, #16 * 12]\n"	\
+	"	ldp x26, x27, [sp, #16 * 13]\n"	\
+	"	ldp x28, x29, [sp, #16 * 14]\n"	\
+	"	ldr x30,   [sp, #16 * 15]\n"
+
+
 #endif /* _ARM_KERNEL_KPROBES_ARM64_H */
diff --git a/arch/arm64/kernel/kprobes.c b/arch/arm64/kernel/kprobes.c
index 2b3ef17..470b537 100644
--- a/arch/arm64/kernel/kprobes.c
+++ b/arch/arm64/kernel/kprobes.c
@@ -561,32 +561,27 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 }
 
 /*
- * Kretprobes: kernel return probes handling
- *
- * AArch64 mode does not support popping the PC value from the
- * stack like on ARM 32-bit (ldmia {..,pc}), so atleast one
- * register need to be used to achieve branching/return.
- * It means return probes cannot return back to the original
- * return address directly without modifying the register context.
- *
- * So like other architectures, we prepare a global routine
- * with NOPs, which serve as trampoline address that hack away the
- * function return, with the exact register context.
- * Placing a kprobe on trampoline routine entry will trap again to
- * execute return probe handlers and restore original return address
- * in ELR_EL1, this way saved pt_regs still hold the original
- * register values to be carried back to the caller.
+ * When a retprobed function returns, this code saves registers and
+ * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
-static void __used kretprobe_trampoline_holder(void)
+static void __used __kprobes kretprobe_trampoline_holder(void)
 {
 	asm volatile (".global kretprobe_trampoline\n"
 			"kretprobe_trampoline:\n"
-			"NOP\n\t"
-			"NOP\n\t");
+		        "sub sp, sp, %0\n"
+			SAVE_REGS_STRING
+			"mov x0, sp\n"
+			"bl trampoline_probe_handler\n"
+			/* Replace trampoline address in lr with actual
+			   orig_ret_addr return address. */
+			"str x0, [sp, #16 * 15]\n"
+			RESTORE_REGS_STRING
+		        "add sp, sp, %0\n"
+			"ret\n"
+		      : : "I"(sizeof(struct pt_regs)) : "memory");
 }
 
-static int __kprobes
-trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs)
 {
 	struct kretprobe_instance *ri = NULL;
 	struct hlist_head *head, empty_rp;
@@ -647,7 +642,7 @@ trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	}
 
 	/* return 1 so that post handlers not called */
-	return 1;
+	return (void *) orig_ret_addr;
 }
 
 void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
@@ -659,18 +654,12 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->regs[30] = (long)&kretprobe_trampoline;
 }
 
-static struct kprobe trampoline = {
-	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
-	.pre_handler = trampoline_probe_handler
-};
-
-int __kprobes arch_trampoline_kprobe(struct kprobe *p)
+int __init arch_init_kprobes(void)
 {
-	return p->addr == (kprobe_opcode_t *) &kretprobe_trampoline;
+	return 0;
 }
 
-int __init arch_init_kprobes(void)
+int arch_trampoline_kprobe(struct kprobe *p)
 {
-	/* register trampoline for kret probe */
-	return register_kprobe(&trampoline);
+	return 0;
 }