x86/srso: Improve i-cache locality for alias mitigation

Move srso_alias_return_thunk() to the same section as
srso_alias_safe_ret() so they can share a cache line.
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/eadaf5530b46a7ae8b936522da45ae555d2b3393.1693889988.git.jpoimboe@kernel.org

arch/x86/lib/retpoline.S

@@ -177,15 +177,14 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	int3
 SYM_FUNC_END(srso_alias_safe_ret)
 
-	.section .text..__x86.return_thunk
-
-SYM_CODE_START(srso_alias_return_thunk)
+SYM_CODE_START_NOALIGN(srso_alias_return_thunk)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
 	call srso_alias_safe_ret
 	ud2
 SYM_CODE_END(srso_alias_return_thunk)
 
+	.section .text..__x86.return_thunk
 /*
  * Some generic notes on the untraining sequences:
  *