x86,nospec: Simplify {JMP,CALL}_NOSPEC

Have {JMP,CALL}_NOSPEC generate the same code GCC does for indirect
calls and rely on the objtool retpoline patching infrastructure.

There's no reason these should be alternatives while the vast bulk of
compiler generated retpolines are not.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

arch/x86/include/asm/nospec-branch.h

@@ -93,6 +93,19 @@
 #endif
 .endm
 
+/*
+ * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
+ * to the retpoline thunk with a CS prefix when the register requires
+ * a RAX prefix byte to encode. Also see apply_retpolines().
+ */
+.macro __CS_PREFIX reg:req
+	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
+	.ifc \reg,\rs
+	.byte 0x2e
+	.endif
+	.endr
+.endm
+
 /*
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
@@ -100,19 +113,18 @@
  */
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
-		      __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
-		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE
+	__CS_PREFIX \reg
+	jmp	__x86_indirect_thunk_\reg
 #else
 	jmp	*%\reg
+	int3
 #endif
 .endm
 
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
-	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
-		      __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
-		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE
+	__CS_PREFIX \reg
+	call	__x86_indirect_thunk_\reg
 #else
 	call	*%\reg
 #endif