From: Thomas Gleixner <tglx@linutronix.de>

Now that all functions are 16 byte aligned, add 16 bytes of NOP
padding in front of each function. This prepares things for software
call stack tracking and kCFI/FineIBT.

This significantly increases kernel .text size, around 5.1% on a
x86_64-defconfig-ish build.

However, per the random access argument used for alignment, these 16
extra bytes are code that wouldn't be used. Performance measurements
back this up by showing no significant performance regressions.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 Makefile                       |    3 +++
 arch/x86/Kconfig               |   12 +++++++++++-
 arch/x86/Makefile              |    5 +++++
 arch/x86/entry/vdso/Makefile   |    3 ++-
 arch/x86/include/asm/linkage.h |   28 ++++++++++++++++++++++++----
 5 files changed, 45 insertions(+), 6 deletions(-)

--- a/Makefile
+++ b/Makefile
@@ -920,6 +920,9 @@ KBUILD_AFLAGS	+= -fno-lto
 export CC_FLAGS_LTO
 endif
 
+PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES)
+export PADDING_CFLAGS
+
 ifdef CONFIG_CFI_CLANG
 CC_FLAGS_CFI	:= -fsanitize=cfi \
 		   -fsanitize-cfi-cross-dso \
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2427,9 +2427,19 @@ config CC_HAS_SLS
 config CC_HAS_RETURN_THUNK
 	def_bool $(cc-option,-mfunction-return=thunk-extern)
 
+config CC_HAS_ENTRY_PADDING
+	def_bool $(cc-option,-fpatchable-function-entry=16,16)
+
+config FUNCTION_PADDING_BYTES
+	int
+	default 32 if CALL_THUNKS_DEBUG && !CFI_CLANG
+	default 27 if CALL_THUNKS_DEBUG && CFI_CLANG
+	default 16 if !CFI_CLANG
+	default 11
+
 config HAVE_CALL_THUNKS
 	def_bool y
-	depends on RETHUNK && OBJTOOL
+	depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL
 
 config CALL_THUNKS
 	def_bool n
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -202,6 +202,11 @@ ifdef CONFIG_SLS
   KBUILD_CFLAGS += -mharden-sls=all
 endif
 
+PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES)
+ifdef CONFIG_CALL_THUNKS
+  KBUILD_CFLAGS += $(PADDING_CFLAGS)
+endif
+
 KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE)
 
 ifdef CONFIG_LTO_CLANG
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -92,7 +92,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
 endif
 endif
 
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(PADDING_CFLAGS) $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
 
 #
@@ -154,6 +154,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(RANDS
 KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(PADDING_CFLAGS),$(KBUILD_CFLAGS_32))
 KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
 KBUILD_CFLAGS_32 += -fno-stack-protector
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -13,17 +13,37 @@
 #endif /* CONFIG_X86_32 */
 
 #if CONFIG_FUNCTION_ALIGNMENT == 8
-#define __ALIGN			.p2align 3, 0x90;
+# define __ALIGN		.p2align 3, 0x90;
 #elif CONFIG_FUNCTION_ALIGNMENT == 16
-#define __ALIGN			.p2align 4, 0x90;
+# define __ALIGN		.p2align 4, 0x90;
+#elif CONFIG_FUNCTION_ALIGNMENT == 32
+# define __ALIGN		.p2align 5, 0x90
 #else
 # error Unsupported function alignment
 #endif
 
 #define __ALIGN_STR		__stringify(__ALIGN)
-#define ASM_FUNC_ALIGN		__ALIGN_STR
-#define __FUNC_ALIGN		__ALIGN
+
+#ifdef CONFIG_CFI_CLANG
+#define __FUNCTION_PADDING	(CONFIG_FUNCTION_ALIGNMENT - 5)
+#else
+#define __FUNCTION_PADDING	CONFIG_FUNCTION_ALIGNMENT
+#endif
+
+#if defined(CONFIG_CALL_THUNKS) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define FUNCTION_PADDING	.skip __FUNCTION_PADDING, 0x90;
+#else
+#define FUNCTION_PADDING
+#endif
+
+#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BULID_VDSO)
+# define __FUNC_ALIGN		__ALIGN; FUNCTION_PADDING
+#else
+# define __FUNC_ALIGN		__ALIGN
+#endif
+
 #define SYM_F_ALIGN		__FUNC_ALIGN
+#define ASM_FUNC_ALIGN		__stringify(__FUNC_ALIGN)
 
 #ifdef __ASSEMBLY__