diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index e835164189f1..c320b3ce7b58 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1951,6 +1951,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG)
 		stack_size += 8; /* room for return value of orig_call */
 
+	if (flags & BPF_TRAMP_F_IP_ARG)
+		stack_size += 8; /* room for IP address argument */
+
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
@@ -1964,6 +1967,22 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
 	EMIT1(0x53);		 /* push rbx */
 
+	if (flags & BPF_TRAMP_F_IP_ARG) {
+		/* Store IP address of the traced function:
+		 * mov rax, QWORD PTR [rbp + 8]
+		 * sub rax, X86_PATCH_SIZE
+		 * mov QWORD PTR [rbp - stack_size], rax
+		 */
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
+		EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE);
+		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size);
+
+		/* Continue with stack_size for regs storage, stack will
+		 * be correctly restored with 'leave' instruction.
+		 */
+		stack_size -= 8;
+	}
+
 	save_regs(m, &prog, nr_args, stack_size);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9a4a480a6d0..94d77dc7ce35 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -579,6 +579,11 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
 
+/* Store IP address of the caller on the trampoline stack,
+ * so it's available for trampoline's programs.
+ */
+#define BPF_TRAMP_F_IP_ARG		BIT(3)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
  */