x86,static_call: Use alternative RET encoding

commit ee88d363d15617ff50ac24fab0ffec11113b2aeb upstream.

In addition to teaching static_call about the new way to spell 'RET',
there is an added complication in that static_call() is allowed to
rewrite text before it is known which particular spelling is required.

In order to deal with this; have a static_call specific fixup in the
apply_return() 'alternative' patching routine that will rewrite the
static_call trampoline to match the definite sequence.

This in turn creates the problem of uniquely identifying static call
trampolines. Currently trampolines are 8 bytes, the first 5 being the
jmp.d32/ret sequence and the final 3 a byte sequence that spells out
'SCT'.

This sequence is used in __static_call_validate() to ensure it is
patching a trampoline and not a random other jmp.d32. That is,
false-positives shouldn't be plenty, but aren't a big concern.

OTOH the new __static_call_fixup() must not have false-positives, and
'SCT' decodes to the somewhat weird but semi plausible sequence:

  push %rbx
  rex.XB push %r12

Additionally, there are SLS concerns with immediate jumps. Combined it
seems like a good moment to change the signature to a single 3 byte
trap instruction that is unique to this usage and will not ever get
generated by accident.

As such, change the signature to: '0x0f, 0xb9, 0xcc', which decodes
to:

  ud1 %esp, %ecx

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
[cascardo: skip validation as introduced by 2105a92748e8 ("static_call,x86: Robustify trampoline patching")]
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
[bwh: Backported to 5.10: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

arch/x86/include/asm/static_call.h

@@ -21,6 +21,16 @@
  * relative displacement across sections.
  */
 
+/*
+ * The trampoline is 8 bytes and of the general form:
+ *
+ *   jmp.d32 \func
+ *   ud1 %esp, %ecx
+ *
+ * That trailing #UD provides both a speculation stop and serves as a unique
+ * 3 byte signature identifying static call trampolines. Also see tramp_ud[]
+ * and __static_call_fixup().
+ */
 #define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns)			\
 	asm(".pushsection .static_call.text, \"ax\"		\n"	\
 	    ".align 4						\n"	\
@@ -34,8 +44,13 @@
 #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)")
 
+#ifdef CONFIG_RETPOLINE
+#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
+	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk")
+#else
 #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name)			\
 	__ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop")
+#endif
 
 
 #define ARCH_ADD_TRAMP_KEY(name)					\
@@ -44,4 +59,6 @@
 	    ".long " STATIC_CALL_KEY_STR(name) " - .		\n"	\
 	    ".popsection					\n")
 
+extern bool __static_call_fixup(void *tramp, u8 op, void *dest);
+
 #endif /* _ASM_STATIC_CALL_H */

arch/x86/kernel/alternative.c

@@ -693,18 +693,22 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 	s32 *s;
 
 	for (s = start; s < end; s++) {
-		void *addr = (void *)s + *s;
+		void *dest = NULL, *addr = (void *)s + *s;
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
-		u8 op1;
+		u8 op;
 
 		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
-		op1 = insn.opcode.bytes[0];
-		if (WARN_ON_ONCE(op1 != JMP32_INSN_OPCODE))
+		op = insn.opcode.bytes[0];
+		if (op == JMP32_INSN_OPCODE)
+			dest = addr + insn.length + insn.immediate.value;
+
+		if (__static_call_fixup(addr, op, dest) ||
+		    WARN_ON_ONCE(dest != &__x86_return_thunk))
 			continue;
 
 		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",

arch/x86/kernel/static_call.c

@@ -11,6 +11,13 @@ enum insn_type {
 	RET = 3,  /* tramp / site cond-tail-call */
 };
 
+/*
+ * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such
+ * that there is no false-positive trampoline identification while also being a
+ * speculation stop.
+ */
+static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc };
+
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
 static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
@@ -32,7 +39,10 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = &retinsn;
+		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+		else
+			code = &retinsn;
 		break;
 	}
 
@@ -97,3 +107,29 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 	mutex_unlock(&text_mutex);
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
+
+#ifdef CONFIG_RETPOLINE
+/*
+ * This is called by apply_returns() to fix up static call trampolines,
+ * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
+ * having a return trampoline.
+ *
+ * The problem is that static_call() is available before determining
+ * X86_FEATURE_RETHUNK and, by implication, running alternatives.
+ *
+ * This means that __static_call_transform() above can have overwritten the
+ * return trampoline and we now need to fix things up to be consistent.
+ */
+bool __static_call_fixup(void *tramp, u8 op, void *dest)
+{
+	if (memcmp(tramp+5, tramp_ud, 3)) {
+		/* Not a trampoline site, not our problem. */
+		return false;
+	}
+
+	if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk)
+		__static_call_transform(tramp, RET, NULL);
+
+	return true;
+}
+#endif