[PATCH v2 10/14] x86/alternative: Handle Jcc __x86_indirect_thunk_\reg

[Peter Zijlstra]

Handle the rare cases where the compiler (clang) does an indirect
conditional tail-call using:

  Jcc __x86_indirect_thunk_\reg

For the !RETPOLINE case this can be rewritten to fit the original (6
byte) instruction like:

  Jncc.d8	1f
  JMP		*%\reg
  NOP
1:

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
---
 arch/x86/kernel/alternative.c |   38 ++++++++++++++++++++++++++++++++++----
 1 file changed, 34 insertions(+), 4 deletions(-)

--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -393,7 +393,8 @@ static int emit_indirect(int op, int reg
 static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 {
 	void (*target)(void);
-	int reg, i = 0;
+	int reg, ret, i = 0;
+	u8 op, cc;
 
 	target = addr + insn->length + insn->immediate.value;
 	reg = (target - &__x86_indirect_thunk_rax) /
@@ -408,9 +409,34 @@ static int patch_retpoline(void *addr, s
 	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE))
 		return -1;
 
-	i = emit_indirect(insn->opcode.bytes[0], reg, bytes);
-	if (i < 0)
-		return i;
+	op = insn->opcode.bytes[0];
+
+	/*
+	 * Convert:
+	 *
+	 *   Jcc.d32 __x86_indirect_thunk_\reg
+	 *
+	 * into:
+	 *
+	 *   Jncc.d8 1f
+	 *   jmp *%\reg
+	 *   nop
+	 * 1:
+	 */
+	if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) {
+		cc = insn->opcode.bytes[1] & 0xf;
+		cc ^= 1; /* invert condition */
+
+		bytes[i++] = 0x70 + cc; /* Jcc.d8 */
+		bytes[i++] = insn->length - 2;
+
+		op = JMP32_INSN_OPCODE;
+	}
+
+	ret = emit_indirect(op, reg, bytes + i);
+	if (ret < 0)
+		return ret;
+	i += ret;
 
 	for (; i < insn->length;)
 		bytes[i++] = BYTES_NOP1;
@@ -444,6 +470,10 @@ void __init_or_module noinline apply_ret
 		case JMP32_INSN_OPCODE:
 			break;
 
+		case 0x0f: /* escape */
+			if (op2 >= 0x80 && op2 <= 0x8f)
+				break;
+			fallthrough;
 		default:
 			WARN_ON_ONCE(1);
 			continue;