KVM: x86: Wrong flags on CMPS and SCAS emulation

CMPS and SCAS instructions are evaluated in the wrong order.  For reference (of
CMPS), see http://www.fermimn.gov.it/linux/quarta/x86/cmps.htm : "Note that the
direction of subtraction for CMPS is [SI] - [DI] or [ESI] - [EDI]. The left
operand (SI or ESI) is the source and the right operand (DI or EDI) is the
destination. This is the reverse of the usual Intel convention in which the
left operand is the destination and the right operand is the source."

Introducing em_cmp_r for this matter that performs comparison in reverse order
using fastop infrastructure to avoid a wrapper function.

Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/emulate.c

@@ -380,6 +380,15 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	ON64(FOP2E(op##q, rax, cl)) \
 	FOP_END
 
+/* 2 operand, src and dest are reversed */
+#define FASTOP2R(op, name) \
+	FOP_START(name) \
+	FOP2E(op##b, dl, al) \
+	FOP2E(op##w, dx, ax) \
+	FOP2E(op##l, edx, eax) \
+	ON64(FOP2E(op##q, rdx, rax)) \
+	FOP_END
+
 #define FOP3E(op,  dst, src, src2) \
 	FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
 
@@ -913,6 +922,8 @@ FASTOP2W(btc);
 
 FASTOP2(xadd);
 
+FASTOP2R(cmp, cmp_r);
+
 static u8 test_cc(unsigned int condition, unsigned long flags)
 {
 	u8 rc;
@@ -3993,12 +4004,12 @@ static const struct opcode opcode_table[256] = {
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
 	I2bv(SrcSI | DstDI | Mov | String, em_mov),
-	F2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
+	F2bv(SrcSI | DstDI | String | NoWrite, em_cmp_r),
 	/* 0xA8 - 0xAF */
 	F2bv(DstAcc | SrcImm | NoWrite, em_test),
 	I2bv(SrcAcc | DstDI | Mov | String, em_mov),
 	I2bv(SrcSI | DstAcc | Mov | String, em_mov),
-	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
+	F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
 	/* 0xB0 - 0xB7 */
 	X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
 	/* 0xB8 - 0xBF */