x86/srso: Disentangle rethunk-dependent options

CONFIG_RETHUNK, CONFIG_CPU_UNRET_ENTRY and CONFIG_CPU_SRSO are all
tangled up.  De-spaghettify the code a bit.

Some of the rethunk-related code has been shuffled around within the
'.text..__x86.return_thunk' section, but otherwise there are no
functional changes.  srso_alias_untrain_ret() and srso_alias_safe_ret()
((which are very address-sensitive) haven't moved.

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/2845084ed303d8384905db3b87b77693945302b4.1693889988.git.jpoimboe@kernel.org

1 files changed, 87 insertions, 70 deletions

diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index a40ba18610d8..8ba79d2b8997 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -126,12 +126,13 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 #endif
-/*
- * This function name is magical and is used by -mfunction-return=thunk-extern
- * for the compiler to generate JMPs to it.
- */
+
 #ifdef CONFIG_RETHUNK
 
+	.section .text..__x86.return_thunk
+
+#ifdef CONFIG_CPU_SRSO
+
 /*
  * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
  * special addresses:
@@ -147,9 +148,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  *
  * As a result, srso_alias_safe_ret() becomes a safe return.
  */
-#ifdef CONFIG_CPU_SRSO
-	.section .text..__x86.rethunk_untrain
-
+	.pushsection .text..__x86.rethunk_untrain
 SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
@@ -157,17 +156,9 @@ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	lfence
 	jmp srso_alias_return_thunk
 SYM_FUNC_END(srso_alias_untrain_ret)
+	.popsection
 
-	.section .text..__x86.rethunk_safe
-#else
-/* dummy definition for alternatives */
-SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
-	ANNOTATE_UNRET_SAFE
-	ret
-	int3
-SYM_FUNC_END(srso_alias_untrain_ret)
-#endif
-
+	.pushsection .text..__x86.rethunk_safe
 SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	lea 8(%_ASM_SP), %_ASM_SP
 	UNWIND_HINT_FUNC
@@ -182,8 +173,58 @@ SYM_CODE_START_NOALIGN(srso_alias_return_thunk)
 	call srso_alias_safe_ret
 	ud2
 SYM_CODE_END(srso_alias_return_thunk)
+	.popsection
+
+/*
+ * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
+ * above. On kernel entry, srso_untrain_ret() is executed which is a
+ *
+ * movabs $0xccccc30824648d48,%rax
+ *
+ * and when the return thunk executes the inner label srso_safe_ret()
+ * later, it is a stack manipulation and a RET which is mispredicted and
+ * thus a "safe" one to use.
+ */
+	.align 64
+	.skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
+SYM_START(srso_untrain_ret, SYM_L_LOCAL, SYM_A_NONE)
+	ANNOTATE_NOENDBR
+	.byte 0x48, 0xb8
+
+/*
+ * This forces the function return instruction to speculate into a trap
+ * (UD2 in srso_return_thunk() below).  This RET will then mispredict
+ * and execution will continue at the return site read from the top of
+ * the stack.
+ */
+SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
+	lea 8(%_ASM_SP), %_ASM_SP
+	ret
+	int3
+	int3
+	/* end of movabs */
+	lfence
+	call srso_safe_ret
+	ud2
+SYM_CODE_END(srso_safe_ret)
+SYM_FUNC_END(srso_untrain_ret)
+
+SYM_CODE_START(srso_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	call srso_safe_ret
+	ud2
+SYM_CODE_END(srso_return_thunk)
+
+#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
+#else /* !CONFIG_CPU_SRSO */
+#define JMP_SRSO_UNTRAIN_RET "ud2"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_SRSO */
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
 
-	.section .text..__x86.return_thunk
 /*
  * Some generic notes on the untraining sequences:
  *
@@ -263,64 +304,21 @@ SYM_CODE_END(retbleed_return_thunk)
 	int3
 SYM_FUNC_END(retbleed_untrain_ret)
 
-/*
- * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
- * above. On kernel entry, srso_untrain_ret() is executed which is a
- *
- * movabs $0xccccc30824648d48,%rax
- *
- * and when the return thunk executes the inner label srso_safe_ret()
- * later, it is a stack manipulation and a RET which is mispredicted and
- * thus a "safe" one to use.
- */
-	.align 64
-	.skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
-SYM_START(srso_untrain_ret, SYM_L_LOCAL, SYM_A_NONE)
-	ANNOTATE_NOENDBR
-	.byte 0x48, 0xb8
+#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret"
+#else /* !CONFIG_CPU_UNRET_ENTRY */
+#define JMP_RETBLEED_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_UNRET_ENTRY */
 
-/*
- * This forces the function return instruction to speculate into a trap
- * (UD2 in srso_return_thunk() below).  This RET will then mispredict
- * and execution will continue at the return site read from the top of
- * the stack.
- */
-SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
-	lea 8(%_ASM_SP), %_ASM_SP
-	ret
-	int3
-	int3
-	/* end of movabs */
-	lfence
-	call srso_safe_ret
-	ud2
-SYM_CODE_END(srso_safe_ret)
-SYM_FUNC_END(srso_untrain_ret)
-
-SYM_CODE_START(srso_return_thunk)
-	UNWIND_HINT_FUNC
-	ANNOTATE_NOENDBR
-	call srso_safe_ret
-	ud2
-SYM_CODE_END(srso_return_thunk)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
-	ALTERNATIVE_2 "jmp retbleed_untrain_ret", \
-		      "jmp srso_untrain_ret", X86_FEATURE_SRSO, \
-		      "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
+	ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET,				\
+		      JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO,		\
+		      JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
 
-SYM_CODE_START(__x86_return_thunk)
-	UNWIND_HINT_FUNC
-	ANNOTATE_NOENDBR
-	ANNOTATE_UNRET_SAFE
-	ret
-	int3
-SYM_CODE_END(__x86_return_thunk)
-EXPORT_SYMBOL(__x86_return_thunk)
-
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
 
 #ifdef CONFIG_CALL_DEPTH_TRACKING
 
@@ -355,3 +353,22 @@ SYM_FUNC_START(__x86_return_skl)
 SYM_FUNC_END(__x86_return_skl)
 
 #endif /* CONFIG_CALL_DEPTH_TRACKING */
+
+/*
+ * This function name is magical and is used by -mfunction-return=thunk-extern
+ * for the compiler to generate JMPs to it.
+ *
+ * This code is only used during kernel boot or module init.  All
+ * 'JMP __x86_return_thunk' sites are changed to something else by
+ * apply_returns().
+ */
+SYM_CODE_START(__x86_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(__x86_return_thunk)
+EXPORT_SYMBOL(__x86_return_thunk)
+
+#endif /* CONFIG_RETHUNK */