x86/its: Add support for ITS-safe return thunk

RETs in the lower half of cacheline may be affected by ITS bug,
specifically when the RSB-underflows. Use ITS-safe return thunk for such
RETs.

RETs that are not patched:

- RET in retpoline sequence does not need to be patched, because the
  sequence itself fills an RSB before RET.
- RET in Call Depth Tracking (CDT) thunks __x86_indirect_{call|jump}_thunk
  and call_depth_return_thunk are not patched because CDT by design
  prevents RSB-underflow.
- RETs in .init section are not reachable after init.
- RETs that are explicitly marked safe with ANNOTATE_UNRET_SAFE.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>
Reviewed-by: Alexandre Chartre <alexandre.chartre@oracle.com>

arch/x86/include/asm/alternative.h

@@ -124,6 +124,20 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
 }
 #endif
 
+#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL)
+extern bool cpu_wants_rethunk(void);
+extern bool cpu_wants_rethunk_at(void *addr);
+#else
+static __always_inline bool cpu_wants_rethunk(void)
+{
+	return false;
+}
+static __always_inline bool cpu_wants_rethunk_at(void *addr)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 extern void alternatives_smp_module_add(struct module *mod, char *name,
 					void *locks, void *locks_end,

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

@@ -367,6 +367,12 @@ static inline void srso_return_thunk(void) {}
 static inline void srso_alias_return_thunk(void) {}
 #endif
 
+#ifdef CONFIG_MITIGATION_ITS
+extern void its_return_thunk(void);
+#else
+static inline void its_return_thunk(void) {}
+#endif
+
 extern void retbleed_return_thunk(void);
 extern void srso_return_thunk(void);
 extern void srso_alias_return_thunk(void);

arch/x86/kernel/alternative.c

@@ -814,6 +814,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 
 #ifdef CONFIG_MITIGATION_RETHUNK
 
+bool cpu_wants_rethunk(void)
+{
+	return cpu_feature_enabled(X86_FEATURE_RETHUNK);
+}
+
+bool cpu_wants_rethunk_at(void *addr)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return false;
+	if (x86_return_thunk != its_return_thunk)
+		return true;
+
+	return !((unsigned long)addr & 0x20);
+}
+
 /*
  * Rewrite the compiler generated return thunk tail-calls.
  *
@@ -830,7 +845,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	int i = 0;
 
 	/* Patch the custom return thunks... */
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk_at(addr)) {
 		i = JMP32_INSN_SIZE;
 		__text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i);
 	} else {
@@ -847,7 +862,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk())
 		static_call_force_reinit();
 
 	for (s = start; s < end; s++) {

arch/x86/kernel/ftrace.c

@@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		goto fail;
 
 	ip = trampoline + size;
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+	if (cpu_wants_rethunk_at(ip))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
 		memcpy(ip, retq, sizeof(retq));

arch/x86/kernel/static_call.c

@@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 		break;
 
 	case RET:
-		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		if (cpu_wants_rethunk_at(insn))
 			code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk);
 		else
 			code = &retinsn;
@@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
 	case JCC:
 		if (!func) {
 			func = __static_call_return;
-			if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			if (cpu_wants_rethunk())
 				func = x86_return_thunk;
 		}
 

arch/x86/kernel/vmlinux.lds.S

@@ -503,6 +503,10 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
 . = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array");
 #endif
 
+#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)
+. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline");
+#endif
+
 #endif /* CONFIG_X86_64 */
 
 /*

arch/x86/lib/retpoline.S

@@ -393,7 +393,18 @@ SYM_CODE_START(__x86_indirect_its_thunk_array)
 	.align 64, 0xcc
 SYM_CODE_END(__x86_indirect_its_thunk_array)
 
-#endif
+.align 64, 0xcc
+.skip 32, 0xcc
+SYM_CODE_START(its_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(its_return_thunk)
+EXPORT_SYMBOL(its_return_thunk)
+
+#endif /* CONFIG_MITIGATION_ITS */
 
 /*
  * This function name is magical and is used by -mfunction-return=thunk-extern

arch/x86/net/bpf_jit_comp.c

@@ -686,7 +686,7 @@ static void emit_return(u8 **pprog, u8 *ip)
 {
 	u8 *prog = *pprog;
 
-	if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) {
+	if (cpu_wants_rethunk()) {
 		emit_jump(&prog, x86_return_thunk, ip);
 	} else {
 		EMIT1(0xC3);		/* ret */