diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 808d4343f6cf..632a83381c2d 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -2847,9 +2847,10 @@ static int get_nr_used_regs(const struct btf_func_model *m)
 }
 
 static void save_args(const struct btf_func_model *m, u8 **prog,
-		      int stack_size, bool for_call_origin)
+		      int stack_size, bool for_call_origin, u32 flags)
 {
 	int arg_regs, first_off = 0, nr_regs = 0, nr_stack_slots = 0;
+	bool use_jmp = bpf_trampoline_use_jmp(flags);
 	int i, j;
 
 	/* Store function arguments to stack.
@@ -2890,7 +2891,7 @@ static void save_args(const struct btf_func_model *m, u8 **prog,
 			 */
 			for (j = 0; j < arg_regs; j++) {
 				emit_ldx(prog, BPF_DW, BPF_REG_0, BPF_REG_FP,
-					 nr_stack_slots * 8 + 0x18);
+					 nr_stack_slots * 8 + 16 + (!use_jmp) * 8);
 				emit_stx(prog, BPF_DW, BPF_REG_FP, BPF_REG_0,
 					 -stack_size);
 
@@ -3284,7 +3285,12 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		 * should be 16-byte aligned. Following code depend on
 		 * that stack_size is already 8-byte aligned.
 		 */
-		stack_size += (stack_size % 16) ? 0 : 8;
+		if (bpf_trampoline_use_jmp(flags)) {
+			/* no rip in the "jmp" case */
+			stack_size += (stack_size % 16) ? 8 : 0;
+		} else {
+			stack_size += (stack_size % 16) ? 0 : 8;
+		}
 	}
 
 	arg_stack_off = stack_size;
@@ -3344,7 +3350,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -ip_off);
 	}
 
-	save_args(m, &prog, regs_off, false);
+	save_args(m, &prog, regs_off, false, flags);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		/* arg1: mov rdi, im */
@@ -3377,7 +3383,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
 		restore_regs(m, &prog, regs_off);
-		save_args(m, &prog, arg_stack_off, true);
+		save_args(m, &prog, arg_stack_off, true, flags);
 
 		if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
 			/* Before calling the original function, load the
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 30fb40421405..2f79afe81482 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1264,6 +1264,18 @@ typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
 bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
 bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return flags & BPF_TRAMP_F_CALL_ORIG && !(flags & BPF_TRAMP_F_SKIP_FRAME);
+}
+#else
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return false;
+}
+#endif
+
 struct bpf_ksym {
 	unsigned long		 start;
 	unsigned long		 end;