[PATCH] x86/speculation: Use AMD specific retpoline for inline asm on AMD

[Zhenzhong Duan <zhenzhong.duan@oracle.com>]

Lfence is preferred than general retpoline on AMD, add this option
in C / inline asm just as the ASM code does.

For x86_64, it still help to have minimal retpoline for kernel even
if gcc doesn't support it, change the inline asm for x86 so that it
could also be used by x86_64.

Add ANNOTATE_NOSPEC_ALTERNATIVE for i386 to avoid below warning:
"warning: objtool: .altinstr_replacement+0x10: unsupported
intra-function call"
"warning: objtool: If this is a retpoline, please patch it
in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE."

Signed-off-by: Zhenzhong Duan <zhenzhong.duan@oracle.com>
---
 arch/x86/include/asm/nospec-branch.h |   23 ++++++++++++++++-------
 1 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index fd2a8c1..2d49eab 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -170,21 +170,26 @@
  */
 # define CALL_NOSPEC						\
 	ANNOTATE_NOSPEC_ALTERNATIVE				\
-	ALTERNATIVE(						\
+	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE)
+	X86_FEATURE_RETPOLINE,					\
+	"lfence;\n"						\
+	ANNOTATE_RETPOLINE_SAFE					\
+	"call *%[thunk_target]\n",				\
+	X86_FEATURE_RETPOLINE_AMD)
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
-#elif defined(CONFIG_X86_32) && defined(CONFIG_RETPOLINE)
+#elif defined(CONFIG_RETPOLINE)
 /*
  * For i386 we use the original ret-equivalent retpoline, because
  * otherwise we'll run out of registers. We don't care about CET
  * here, anyway.
  */
 # define CALL_NOSPEC						\
-	ALTERNATIVE(						\
+	ANNOTATE_NOSPEC_ALTERNATIVE				\
+	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
 	"       jmp    904f;\n"					\
@@ -194,12 +199,16 @@
 	"    	lfence;\n"					\
 	"       jmp    902b;\n"					\
 	"       .align 16\n"					\
-	"903:	addl   $4, %%esp;\n"				\
-	"       pushl  %[thunk_target];\n"			\
+	"903:	add   $4, %%" _ASM_SP ";\n"			\
+	"       push  %[thunk_target];\n"			\
 	"       ret;\n"						\
 	"       .align 16\n"					\
 	"904:	call   901b;\n",				\
-	X86_FEATURE_RETPOLINE)
+	X86_FEATURE_RETPOLINE,					\
+	"lfence;\n"						\
+	ANNOTATE_RETPOLINE_SAFE					\
+	"call *%[thunk_target]\n",				\
+	X86_FEATURE_RETPOLINE_AMD)
 
 # define THUNK_TARGET(addr) [thunk_target] "rm" (addr)
 #else /* No retpoline for C / inline asm */
-- 
1.7.3