x86/speculation: Add a conditional CS prefix to CALL_NOSPEC

Retpoline mitigation for spectre-v2 uses thunks for indirect branches. To
support this mitigation compilers add a CS prefix with
-mindirect-branch-cs-prefix. For an indirect branch in asm, this needs to
be added manually.

CS prefix is already being added to indirect branches in asm files, but not
in inline asm. Add CS prefix to CALL_NOSPEC for inline asm as well. There
is no JMP_NOSPEC for inline asm.

Reported-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-2-96599fed0f33@linux.intel.com

Author: pa1gupta

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

@@ -198,9 +198,8 @@
 .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().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -420,12 +419,24 @@ static inline void call_depth_return_thunk(void) {}
 
 #ifdef CONFIG_X86_64
 
+/*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
 /*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
 #ifdef CONFIG_MITIGATION_RETPOLINE
-#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
 #else
 #define CALL_NOSPEC	"call *%[thunk_target]\n"
 #endif