[RFC] x86/retpoline: Add clang support for 64-bit builds

[Guenter Roeck]

clang has its own set of compiler options for retpoline support.
Also, the thunks required by C code have their own function names.

For 64-bit builds, there is only a single thunk, which is easy
to support. Support for 32-bit builds is more complicated - in
addition to various register thunks, there is also a thunk
named __llvm_external_retpoline_push which is more challenging.
Play it safe and only support 64-bit clang builds for now.

Link: https://github.com/llvm-mirror/clang/commit/0d816739a82da29748caf88570affb9715e18b69
Cc: David Woodhouse <dwmw@xxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: gnomes@xxxxxxxxxxxxxxxxxxx
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: thomas.lendacky@xxxxxxx
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Jiri Kosina <jikos@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxxx>
Cc: Paul Turner <pjt@xxxxxxxxxx>
Signed-off-by: Guenter Roeck <linux@xxxxxxxxxxxx>
---
Sent as RFC because I am not sure if the 64-bit only solution
is acceptable.

 arch/x86/Makefile        |  5 ++++-
 arch/x86/lib/retpoline.S | 24 ++++++++++++++++++++----
 2 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index fad55160dcb9..536dd6775988 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -232,7 +232,10 @@ KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 
 # Avoid indirect branches in kernel to deal with Spectre
 ifdef CONFIG_RETPOLINE
-    RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+    RETPOLINE_CFLAGS = $(call cc-option,-mindirect-branch=thunk-extern -mindirect-branch-register)
+    ifeq ($(RETPOLINE_CFLAGS)$(CONFIG_X86_32),)
+	RETPOLINE_CFLAGS = $(call cc-option,-mretpoline -mretpoline-external-thunk)
+    endif
     ifneq ($(RETPOLINE_CFLAGS),)
         KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) -DRETPOLINE
     endif
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 480edc3a5e03..f77738b13481 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -9,14 +9,22 @@
 #include <asm/nospec-branch.h>
 #include <asm/bitsperlong.h>
 
-.macro THUNK reg
+.macro _THUNK prefix, reg
 	.section .text.__x86.indirect_thunk
 
-ENTRY(__x86_indirect_thunk_\reg)
+ENTRY(\prefix\reg)
 	CFI_STARTPROC
 	JMP_NOSPEC %\reg
 	CFI_ENDPROC
-ENDPROC(__x86_indirect_thunk_\reg)
+ENDPROC(\prefix\reg)
+.endm
+
+.macro THUNK reg
+_THUNK __x86_indirect_thunk_ \reg
+.endm
+
+.macro CLANG_THUNK reg
+_THUNK __llvm_external_retpoline_ \reg
 .endm
 
 /*
@@ -27,8 +35,11 @@ ENDPROC(__x86_indirect_thunk_\reg)
  * the simple and nasty way...
  */
 #define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
-#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
+#define _EXPORT_THUNK(thunk, reg) __EXPORT_THUNK(thunk ## reg)
+#define EXPORT_THUNK(reg) _EXPORT_THUNK(__x86_indirect_thunk_, reg)
 #define GENERATE_THUNK(reg) THUNK reg ; EXPORT_THUNK(reg)
+#define EXPORT_CLANG_THUNK(reg) _EXPORT_THUNK(__llvm_external_retpoline_, reg)
+#define GENERATE_CLANG_THUNK(reg) CLANG_THUNK reg ; EXPORT_CLANG_THUNK(reg)
 
 GENERATE_THUNK(_ASM_AX)
 GENERATE_THUNK(_ASM_BX)
@@ -46,6 +57,11 @@ GENERATE_THUNK(r12)
 GENERATE_THUNK(r13)
 GENERATE_THUNK(r14)
 GENERATE_THUNK(r15)
+
+#ifdef __clang__
+GENERATE_CLANG_THUNK(r11)
+#endif
+
 #endif
 
 /*
-- 
2.7.4