x86/retpoline: Create a retpoline thunk array

Stick all the retpolines in a single symbol and have the individual
thunks as inner labels, this should guarantee thunk order and layout.

Previously there were 16 (or rather 15 without rsp) separate symbols and
a toolchain might reasonably expect it could displace them however it
liked, with disregard for their relative position.

However, now they're part of a larger symbol. Any change to their
relative position would disrupt this larger _array symbol and thus not
be sound.

This is the same reasoning used for data symbols. On their own there
is no guarantee about their relative position wrt to one aonther, but
we're still able to do arrays because an array as a whole is a single
larger symbol.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Tested-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/r/20211026120310.169659320@infradead.org

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

@@ -12,6 +12,8 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 
+#define RETPOLINE_THUNK_SIZE	32
+
 /*
  * Fill the CPU return stack buffer.
  *
@@ -120,11 +122,15 @@
 
 #ifdef CONFIG_RETPOLINE
 
+typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+
 #define GEN(reg) \
-	extern asmlinkage void __x86_indirect_thunk_ ## reg (void);
+	extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
+extern retpoline_thunk_t __x86_indirect_thunk_array[];
+
 #ifdef CONFIG_X86_64
 
 /*

arch/x86/lib/retpoline.S

@@ -28,16 +28,14 @@
 
 .macro THUNK reg
 
-	.align 32
-
-SYM_FUNC_START(__x86_indirect_thunk_\reg)
+	.align RETPOLINE_THUNK_SIZE
+SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
+	UNWIND_HINT_EMPTY
 
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
 		      __stringify(RETPOLINE \reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_AMD
 
-SYM_FUNC_END(__x86_indirect_thunk_\reg)
-
 .endm
 
 /*
@@ -55,10 +53,16 @@ SYM_FUNC_END(__x86_indirect_thunk_\reg)
 #define __EXPORT_THUNK(sym)	_ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym)
 #define EXPORT_THUNK(reg)	__EXPORT_THUNK(__x86_indirect_thunk_ ## reg)
 
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_START(__x86_indirect_thunk_array)
+
 #define GEN(reg) THUNK reg
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 
+	.align RETPOLINE_THUNK_SIZE
+SYM_CODE_END(__x86_indirect_thunk_array)
+
 #define GEN(reg) EXPORT_THUNK(reg)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN