KVM: x86: Distinguish between stack operation and near branches

In 64-bit, stack operations default to 64-bits, but can be overriden (to
16-bit) using opsize override prefix. In contrast, near-branches are always
64-bit.  This patch distinguish between the different behaviors.

Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 147f3fd..a90fa18 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -166,6 +166,7 @@
 #define CheckPerm   ((u64)1 << 49)  /* Has valid check_perm field */
 #define NoBigReal   ((u64)1 << 50)  /* No big real mode */
 #define PrivUD      ((u64)1 << 51)  /* #UD instead of #GP on CPL > 0 */
+#define NearBranch  ((u64)1 << 52)  /* Near branches */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -3771,9 +3772,9 @@
 static const struct opcode group5[] = {
 	F(DstMem | SrcNone | Lock,		em_inc),
 	F(DstMem | SrcNone | Lock,		em_dec),
-	I(SrcMem | Stack,			em_call_near_abs),
+	I(SrcMem | NearBranch,			em_call_near_abs),
 	I(SrcMemFAddr | ImplicitOps | Stack,	em_call_far),
-	I(SrcMem | Stack,			em_jmp_abs),
+	I(SrcMem | NearBranch,			em_jmp_abs),
 	I(SrcMemFAddr | ImplicitOps,		em_jmp_far),
 	I(SrcMem | Stack,			em_push), D(Undefined),
 };
@@ -3955,7 +3956,7 @@
 	I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
 	I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
 	/* 0x70 - 0x7F */
-	X16(D(SrcImmByte)),
+	X16(D(SrcImmByte | NearBranch)),
 	/* 0x80 - 0x87 */
 	G(ByteOp | DstMem | SrcImm, group1),
 	G(DstMem | SrcImm, group1),
@@ -3994,8 +3995,8 @@
 	X8(I(DstReg | SrcImm64 | Mov, em_mov)),
 	/* 0xC0 - 0xC7 */
 	G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
-	I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
-	I(ImplicitOps | Stack, em_ret),
+	I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm),
+	I(ImplicitOps | NearBranch, em_ret),
 	I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
 	I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg),
 	G(ByteOp, group11), G(0, group11),
@@ -4015,13 +4016,14 @@
 	/* 0xD8 - 0xDF */
 	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
 	/* 0xE0 - 0xE7 */
-	X3(I(SrcImmByte, em_loop)),
-	I(SrcImmByte, em_jcxz),
+	X3(I(SrcImmByte | NearBranch, em_loop)),
+	I(SrcImmByte | NearBranch, em_jcxz),
 	I2bvIP(SrcImmUByte | DstAcc, em_in,  in,  check_perm_in),
 	I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
 	/* 0xE8 - 0xEF */
-	I(SrcImm | Stack, em_call), D(SrcImm | ImplicitOps),
-	I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps),
+	I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch),
+	I(SrcImmFAddr | No64, em_jmp_far),
+	D(SrcImmByte | ImplicitOps | NearBranch),
 	I2bvIP(SrcDX | DstAcc, em_in,  in,  check_perm_in),
 	I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out),
 	/* 0xF0 - 0xF7 */
@@ -4081,7 +4083,7 @@
 	N, N, N, N,
 	N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f),
 	/* 0x80 - 0x8F */
-	X16(D(SrcImm)),
+	X16(D(SrcImm | NearBranch)),
 	/* 0x90 - 0x9F */
 	X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
 	/* 0xA0 - 0xA7 */
@@ -4550,7 +4552,7 @@
 		return EMULATION_FAILED;
 
 	if (unlikely(ctxt->d &
-		     (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+	    (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm|NearBranch))) {
 		/*
 		 * These are copied unconditionally here, and checked unconditionally
 		 * in x86_emulate_insn.
@@ -4561,8 +4563,12 @@
 		if (ctxt->d & NotImpl)
 			return EMULATION_FAILED;
 
-		if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
-			ctxt->op_bytes = 8;
+		if (mode == X86EMUL_MODE_PROT64) {
+			if (ctxt->op_bytes == 4 && (ctxt->d & Stack))
+				ctxt->op_bytes = 8;
+			else if (ctxt->d & NearBranch)
+				ctxt->op_bytes = 8;
+		}
 
 		if (ctxt->d & Op3264) {
 			if (mode == X86EMUL_MODE_PROT64)