KVM: x86: POP [ESP] is not emulated correctly

According to Intel SDM: "If the ESP register is used as a base register for
addressing a destination operand in memory, the POP instruction computes the
effective address of the operand after it increments the ESP register."

The current emulation does not behave so. The fix required to waste another
of the precious instruction flags and to check the flag in decode_modrm.
Signed-off-by: Nadav Amit <namit@cs.technion.ac.il>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/emulate.c

@@ -170,6 +170,7 @@
 #define PrivUD      ((u64)1 << 51)  /* #UD instead of #GP on CPL > 0 */
 #define NearBranch  ((u64)1 << 52)  /* Near branches */
 #define No16	    ((u64)1 << 53)  /* No 16 bit operand */
+#define IncSP       ((u64)1 << 54)  /* SP is incremented before ModRM calc */
 
 #define DstXacc     (DstAccLo | SrcAccHi | SrcWrite)
 
@@ -1227,6 +1228,10 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 			else {
 				modrm_ea += reg_read(ctxt, base_reg);
 				adjust_modrm_seg(ctxt, base_reg);
+				/* Increment ESP on POP [ESP] */
+				if ((ctxt->d & IncSP) &&
+				    base_reg == VCPU_REGS_RSP)
+					modrm_ea += ctxt->op_bytes;
 			}
 			if (index_reg != 4)
 				modrm_ea += reg_read(ctxt, index_reg) << scale;
@@ -3758,7 +3763,7 @@ static const struct opcode group1[] = {
 };
 
 static const struct opcode group1A[] = {
-	I(DstMem | SrcNone | Mov | Stack, em_pop), N, N, N, N, N, N, N,
+	I(DstMem | SrcNone | Mov | Stack | IncSP, em_pop), N, N, N, N, N, N, N,
 };
 
 static const struct opcode group2[] = {