From c1dc646f73bd948edbf0c4a7f1baa93ecf8c208e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Sun, 6 Sep 2020 08:11:32 +0900
Subject: [PATCH] lto: test module

Here is a great example for LTO:
  https://llvm.org/docs/LinkTimeOptimization.html

LTO removes foo2() and foo3() from the final executable file, "main".
(and foo4() is also dropped if you pass -flto to main.c)

This patch integrates the example code into a kernel module.

  a.c      ->   kernel/lto-test-a.c
  main.c   ->   kernel/lto-test-main.c

Of course, I replaced printf() with printk().

I applied this test patch on top of Sami's v2:
  https://patchwork.kernel.org/project/linux-kbuild/list/?series=343153

I compiled arm64 defconfig + CONFIG_LTO_CLANG.

This is the result:

$ aarch64-linux-gnu-nm kernel/lto-test.ko
0000000000000010 T foo1
0000000000000000 T foo2
000000000000004c T foo4
0000000000000000 B i.llvm.7710645642085602891
0000000000000000 r __kstrtab_lto_test_main
000000000000000e r __kstrtabns_lto_test_main
0000000000000000 r __ksymtab_lto_test_main
0000000000000068 T lto_test_main
0000000000000000 r _note_7
                 U printk
0000000000000000 R .str.llvm.887650332484512380
0000000000000000 D __this_module
0000000000000063 r __UNIQUE_ID_depends254
000000000000005a r __UNIQUE_ID_intree253
000000000000004c r __UNIQUE_ID_name252
0000000000000000 r __UNIQUE_ID_vermagic251

Modules are relocatable objects, not executables.
How can clang LTO know unreachable symbols are really
unreachable?

According to the result above, foo2 is remaining.

The behavior is the same for obj-y because LTO is run against
vmlinux.o, which is a relocatable ELF.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 kernel/Makefile        |  3 +++
 kernel/lto-test-a.c    | 22 ++++++++++++++++++++++
 kernel/lto-test-a.h    |  3 +++
 kernel/lto-test-main.c | 12 ++++++++++++
 4 files changed, 40 insertions(+)
 create mode 100644 kernel/lto-test-a.c
 create mode 100644 kernel/lto-test-a.h
 create mode 100644 kernel/lto-test-main.c

diff --git a/kernel/Makefile b/kernel/Makefile
index 9a20016d4900..2111251c2093 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -147,3 +147,6 @@ $(obj)/kheaders_data.tar.xz: FORCE
 	$(call cmd,genikh)
 
 clean-files := kheaders_data.tar.xz kheaders.md5
+
+obj-m += lto-test.o
+lto-test-objs := lto-test-a.o lto-test-main.o
diff --git a/kernel/lto-test-a.c b/kernel/lto-test-a.c
new file mode 100644
index 000000000000..15cdc320ec1e
--- /dev/null
+++ b/kernel/lto-test-a.c
@@ -0,0 +1,22 @@
+#include "lto-test-a.h"
+
+static signed int i = 0;
+
+void foo2(void) {
+  i = -1;
+}
+
+static int foo3(void) {
+  foo4();
+  return 10;
+}
+
+int foo1(void) {
+  int data = 0;
+
+  if (i < 0)
+    data = foo3();
+
+  data = data + 42;
+  return data;
+}
diff --git a/kernel/lto-test-a.h b/kernel/lto-test-a.h
new file mode 100644
index 000000000000..fca4d13a52e0
--- /dev/null
+++ b/kernel/lto-test-a.h
@@ -0,0 +1,3 @@
+extern int foo1(void);
+extern void foo2(void);
+extern void foo4(void);
diff --git a/kernel/lto-test-main.c b/kernel/lto-test-main.c
new file mode 100644
index 000000000000..6e8caa2c7667
--- /dev/null
+++ b/kernel/lto-test-main.c
@@ -0,0 +1,12 @@
+#include <linux/module.h>
+#include <linux/export.h>
+#include "lto-test-a.h"
+
+void foo4(void) {
+  printk("Hi\n");
+}
+
+int lto_test_main(void) {
+  return foo1();
+}
+EXPORT_SYMBOL(lto_test_main);
-- 
2.25.1