x86: Use return-thunk in asm code

Use the return thunk in asm code. If the thunk isn't needed, it will
get patched into a RET instruction during boot by apply_returns().

Since alternatives can't handle relocations outside of the first
instruction, putting a 'jmp __x86_return_thunk' in one is not valid,
therefore carve out the memmove ERMS path into a separate label and jump
to it.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>
Reviewed-by: Josh Poimboeuf <[email protected]>
Signed-off-by: Borislav Petkov <[email protected]>

Author: Peter Zijlstra

arch/x86/entry/vdso/Makefile

@@ -92,6 +92,7 @@ endif
 endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
 
 #
 # vDSO code runs in userspace and -pg doesn't help with profiling anyway.

arch/x86/include/asm/linkage.h

@@ -19,19 +19,27 @@
 #define __ALIGN_STR	__stringify(__ALIGN)
 #endif
 
+#if defined(CONFIG_RETPOLINE) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define RET	jmp __x86_return_thunk
+#else /* CONFIG_RETPOLINE */
 #ifdef CONFIG_SLS
 #define RET	ret; int3
 #else
 #define RET	ret
 #endif
+#endif /* CONFIG_RETPOLINE */
 
 #else /* __ASSEMBLY__ */
 
+#if defined(CONFIG_RETPOLINE) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
+#define ASM_RET	"jmp __x86_return_thunk\n\t"
+#else /* CONFIG_RETPOLINE */
 #ifdef CONFIG_SLS
 #define ASM_RET	"ret; int3\n\t"
 #else
 #define ASM_RET	"ret\n\t"
 #endif
+#endif /* CONFIG_RETPOLINE */
 
 #endif /* __ASSEMBLY__ */
 

arch/x86/lib/memmove_64.S

@@ -39,7 +39,7 @@ SYM_FUNC_START(__memmove)
 	/* FSRM implies ERMS => no length checks, do the copy directly */
 .Lmemmove_begin_forward:
 	ALTERNATIVE "cmp $0x20, %rdx; jb 1f", "", X86_FEATURE_FSRM
-	ALTERNATIVE "", __stringify(movq %rdx, %rcx; rep movsb; RET), X86_FEATURE_ERMS
+	ALTERNATIVE "", "jmp .Lmemmove_erms", X86_FEATURE_ERMS
 
 	/*
 	 * movsq instruction have many startup latency
@@ -205,6 +205,11 @@ SYM_FUNC_START(__memmove)
 	movb %r11b, (%rdi)
 13:
 	RET
+
+.Lmemmove_erms:
+	movq %rdx, %rcx
+	rep movsb
+	RET
 SYM_FUNC_END(__memmove)
 EXPORT_SYMBOL(__memmove)