#define DstAcc (4<<1) /* Destination Accumulator */
#define DstDI (5<<1) /* Destination is in ES:(E)DI */
#define DstMem64 (6<<1) /* 64bit memory operand */
+#define DstImmUByte (7<<1) /* 8-bit unsigned immediate operand */
#define DstMask (7<<1)
/* Source operand type. */
#define SrcNone (0<<4) /* No source operand. */
-#define SrcImplicit (0<<4) /* Source operand is implicit in the opcode. */
#define SrcReg (1<<4) /* Register operand. */
#define SrcMem (2<<4) /* Memory operand. */
#define SrcMem16 (3<<4) /* Memory operand (16-bit). */
#define SrcImmFAddr (0xb<<4) /* Source is immediate far address */
#define SrcMemFAddr (0xc<<4) /* Source is far address in memory */
#define SrcAcc (0xd<<4) /* Source Accumulator */
+#define SrcImmU16 (0xe<<4) /* Immediate operand, unsigned, 16 bits */
#define SrcMask (0xf<<4)
/* Generic ModRM decode. */
#define ModRM (1<<8)
#define Src2CL (1<<29)
#define Src2ImmByte (2<<29)
#define Src2One (3<<29)
+#define Src2Imm (4<<29)
#define Src2Mask (7<<29)
#define X2(x...) x, x
#define ON64(x)
#endif
-#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix) \
+#define ____emulate_2op(_op, _src, _dst, _eflags, _x, _y, _suffix, _dsttype) \
do { \
__asm__ __volatile__ ( \
_PRE_EFLAGS("0", "4", "2") \
_op _suffix " %"_x"3,%1; " \
_POST_EFLAGS("0", "4", "2") \
- : "=m" (_eflags), "=m" ((_dst).val), \
+ : "=m" (_eflags), "+q" (*(_dsttype*)&(_dst).val),\
"=&r" (_tmp) \
: _y ((_src).val), "i" (EFLAGS_MASK)); \
} while (0)
\
switch ((_dst).bytes) { \
case 2: \
- ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w"); \
+ ____emulate_2op(_op,_src,_dst,_eflags,_wx,_wy,"w",u16);\
break; \
case 4: \
- ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l"); \
+ ____emulate_2op(_op,_src,_dst,_eflags,_lx,_ly,"l",u32);\
break; \
case 8: \
- ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q")); \
+ ON64(____emulate_2op(_op,_src,_dst,_eflags,_qx,_qy,"q",u64)); \
break; \
} \
} while (0)
unsigned long _tmp; \
switch ((_dst).bytes) { \
case 1: \
- ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b"); \
+ ____emulate_2op(_op,_src,_dst,_eflags,_bx,_by,"b",u8); \
break; \
default: \
__emulate_2op_nobyte(_op, _src, _dst, _eflags, \
return X86EMUL_PROPAGATE_FAULT;
}
+static void write_register_operand(struct operand *op)
+{
+ /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */
+ switch (op->bytes) {
+ case 1:
+ *(u8 *)op->addr.reg = (u8)op->val;
+ break;
+ case 2:
+ *(u16 *)op->addr.reg = (u16)op->val;
+ break;
+ case 4:
+ *op->addr.reg = (u32)op->val;
+ break; /* 64b: zero-extend */
+ case 8:
+ *op->addr.reg = op->val;
+ break;
+ }
+}
+
static inline int writeback(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops)
{
switch (c->dst.type) {
case OP_REG:
- /* The 4-byte case *is* correct:
- * in 64-bit mode we zero-extend.
- */
- switch (c->dst.bytes) {
- case 1:
- *(u8 *)c->dst.addr.reg = (u8)c->dst.val;
- break;
- case 2:
- *(u16 *)c->dst.addr.reg = (u16)c->dst.val;
- break;
- case 4:
- *c->dst.addr.reg = (u32)c->dst.val;
- break; /* 64b: zero-ext */
- case 8:
- *c->dst.addr.reg = c->dst.val;
- break;
- }
+ write_register_operand(&c->dst);
break;
case OP_MEM:
if (c->lock_prefix)
struct x86_emulate_ops *ops, int irq)
{
struct decode_cache *c = &ctxt->decode;
- int rc = X86EMUL_CONTINUE;
+ int rc;
struct desc_ptr dt;
gva_t cs_addr;
gva_t eip_addr;
/* TODO: Add limit checks */
c->src.val = ctxt->eflags;
emulate_push(ctxt, ops);
+ rc = writeback(ctxt, ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
ctxt->eflags &= ~(EFLG_IF | EFLG_TF | EFLG_AC);
c->src.val = ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
emulate_push(ctxt, ops);
+ rc = writeback(ctxt, ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
c->src.val = c->eip;
emulate_push(ctxt, ops);
+ rc = writeback(ctxt, ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ c->dst.type = OP_NONE;
ops->get_idt(&dt, ctxt->vcpu);
return rc;
}
+static int emulate_load_segment(struct x86_emulate_ctxt *ctxt,
+ struct x86_emulate_ops *ops, int seg)
+{
+ struct decode_cache *c = &ctxt->decode;
+ unsigned short sel;
+ int rc;
+
+ memcpy(&sel, c->src.valptr + c->op_bytes, 2);
+
+ rc = load_segment_descriptor(ctxt, ops, sel, seg);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ c->dst.val = c->src.val;
+ return rc;
+}
+
static inline void
setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
struct x86_emulate_ops *ops, struct desc_struct *cs,
return X86EMUL_CONTINUE;
}
+static int em_das(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+ u8 al, old_al;
+ bool af, cf, old_cf;
+
+ cf = ctxt->eflags & X86_EFLAGS_CF;
+ al = c->dst.val;
+
+ old_al = al;
+ old_cf = cf;
+ cf = false;
+ af = ctxt->eflags & X86_EFLAGS_AF;
+ if ((al & 0x0f) > 9 || af) {
+ al -= 6;
+ cf = old_cf | (al >= 250);
+ af = true;
+ } else {
+ af = false;
+ }
+ if (old_al > 0x99 || old_cf) {
+ al -= 0x60;
+ cf = true;
+ }
+
+ c->dst.val = al;
+ /* Set PF, ZF, SF */
+ c->src.type = OP_IMM;
+ c->src.val = 0;
+ c->src.bytes = 1;
+ emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags);
+ ctxt->eflags &= ~(X86_EFLAGS_AF | X86_EFLAGS_CF);
+ if (cf)
+ ctxt->eflags |= X86_EFLAGS_CF;
+ if (af)
+ ctxt->eflags |= X86_EFLAGS_AF;
+ return X86EMUL_CONTINUE;
+}
+
+static int em_call_far(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+ u16 sel, old_cs;
+ ulong old_eip;
+ int rc;
+
+ old_cs = ctxt->ops->get_segment_selector(VCPU_SREG_CS, ctxt->vcpu);
+ old_eip = c->eip;
+
+ memcpy(&sel, c->src.valptr + c->op_bytes, 2);
+ if (load_segment_descriptor(ctxt, ctxt->ops, sel, VCPU_SREG_CS))
+ return X86EMUL_CONTINUE;
+
+ c->eip = 0;
+ memcpy(&c->eip, c->src.valptr, c->op_bytes);
+
+ c->src.val = old_cs;
+ emulate_push(ctxt, ctxt->ops);
+ rc = writeback(ctxt, ctxt->ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ c->src.val = old_eip;
+ emulate_push(ctxt, ctxt->ops);
+ rc = writeback(ctxt, ctxt->ops);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+
+ c->dst.type = OP_NONE;
+
+ return X86EMUL_CONTINUE;
+}
+
+static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+ int rc;
+
+ c->dst.type = OP_REG;
+ c->dst.addr.reg = &c->eip;
+ c->dst.bytes = c->op_bytes;
+ rc = emulate_pop(ctxt, ctxt->ops, &c->dst.val, c->op_bytes);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ register_address_increment(c, &c->regs[VCPU_REGS_RSP], c->src.val);
+ return X86EMUL_CONTINUE;
+}
+
+static int em_imul(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+
+ emulate_2op_SrcV_nobyte("imul", c->src, c->dst, ctxt->eflags);
+ return X86EMUL_CONTINUE;
+}
+
+static int em_imul_3op(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+
+ c->dst.val = c->src2.val;
+ return em_imul(ctxt);
+}
+
+static int em_cwd(struct x86_emulate_ctxt *ctxt)
+{
+ struct decode_cache *c = &ctxt->decode;
+
+ c->dst.type = OP_REG;
+ c->dst.bytes = c->src.bytes;
+ c->dst.addr.reg = &c->regs[VCPU_REGS_RDX];
+ c->dst.val = ~((c->src.val >> (c->src.bytes * 8 - 1)) - 1);
+
+ return X86EMUL_CONTINUE;
+}
+
+static int em_rdtsc(struct x86_emulate_ctxt *ctxt)
+{
+ unsigned cpl = ctxt->ops->cpl(ctxt->vcpu);
+ struct decode_cache *c = &ctxt->decode;
+ u64 tsc = 0;
+
+ if (cpl > 0 && (ctxt->ops->get_cr(4, ctxt->vcpu) & X86_CR4_TSD)) {
+ emulate_gp(ctxt, 0);
+ return X86EMUL_PROPAGATE_FAULT;
+ }
+ ctxt->ops->get_msr(ctxt->vcpu, MSR_IA32_TSC, &tsc);
+ c->regs[VCPU_REGS_RAX] = (u32)tsc;
+ c->regs[VCPU_REGS_RDX] = tsc >> 32;
+ return X86EMUL_CONTINUE;
+}
+
#define D(_y) { .flags = (_y) }
#define N D(0)
#define G(_f, _g) { .flags = ((_f) | Group), .u.group = (_g) }
static struct opcode group5[] = {
D(DstMem | SrcNone | ModRM | Lock), D(DstMem | SrcNone | ModRM | Lock),
- D(SrcMem | ModRM | Stack), N,
+ D(SrcMem | ModRM | Stack),
+ I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far),
D(SrcMem | ModRM | Stack), D(SrcMemFAddr | ModRM | ImplicitOps),
D(SrcMem | ModRM | Stack), N,
};
/* 0x28 - 0x2F */
D(ByteOp | DstMem | SrcReg | ModRM | Lock), D(DstMem | SrcReg | ModRM | Lock),
D(ByteOp | DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM),
- D(ByteOp | DstAcc | SrcImmByte), D(DstAcc | SrcImm), N, N,
+ D(ByteOp | DstAcc | SrcImmByte), D(DstAcc | SrcImm),
+ N, I(ByteOp | DstAcc | No64, em_das),
/* 0x30 - 0x37 */
D(ByteOp | DstMem | SrcReg | ModRM | Lock), D(DstMem | SrcReg | ModRM | Lock),
D(ByteOp | DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM),
N, D(DstReg | SrcMem32 | ModRM | Mov) /* movsxd (x86/64) */ ,
N, N, N, N,
/* 0x68 - 0x6F */
- I(SrcImm | Mov | Stack, em_push), N,
- I(SrcImmByte | Mov | Stack, em_push), N,
+ I(SrcImm | Mov | Stack, em_push),
+ I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op),
+ I(SrcImmByte | Mov | Stack, em_push),
+ I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op),
D(DstDI | ByteOp | Mov | String), D(DstDI | Mov | String), /* insb, insw/insd */
D(SrcSI | ByteOp | ImplicitOps | String), D(SrcSI | ImplicitOps | String), /* outsb, outsw/outsd */
/* 0x70 - 0x7F */
/* 0x90 - 0x97 */
X8(D(SrcAcc | DstReg)),
/* 0x98 - 0x9F */
- N, N, D(SrcImmFAddr | No64), N,
+ D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd),
+ I(SrcImmFAddr | No64, em_call_far), N,
D(ImplicitOps | Stack), D(ImplicitOps | Stack), N, N,
/* 0xA0 - 0xA7 */
D(ByteOp | DstAcc | SrcMem | Mov | MemAbs), D(DstAcc | SrcMem | Mov | MemAbs),
D(DstAcc | SrcImmByte | ByteOp), D(DstAcc | SrcImm),
D(ByteOp | SrcAcc | DstDI | Mov | String), D(SrcAcc | DstDI | Mov | String),
D(ByteOp | SrcSI | DstAcc | Mov | String), D(SrcSI | DstAcc | Mov | String),
- D(ByteOp | DstDI | String), D(DstDI | String),
+ D(ByteOp | SrcAcc | DstDI | String), D(SrcAcc | DstDI | String),
/* 0xB0 - 0xB7 */
X8(D(ByteOp | DstReg | SrcImm | Mov)),
/* 0xB8 - 0xBF */
X8(D(DstReg | SrcImm | Mov)),
/* 0xC0 - 0xC7 */
D(ByteOp | DstMem | SrcImm | ModRM), D(DstMem | SrcImmByte | ModRM),
- N, D(ImplicitOps | Stack), N, N,
+ I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
+ D(ImplicitOps | Stack),
+ D(DstReg | SrcMemFAddr | ModRM | No64), D(DstReg | SrcMemFAddr | ModRM | No64),
D(ByteOp | DstMem | SrcImm | ModRM | Mov), D(DstMem | SrcImm | ModRM | Mov),
/* 0xC8 - 0xCF */
N, N, N, D(ImplicitOps | Stack),
D(ImplicitOps), D(SrcImmByte), D(ImplicitOps | No64), D(ImplicitOps),
/* 0xD0 - 0xD7 */
D(ByteOp | DstMem | SrcOne | ModRM), D(DstMem | SrcOne | ModRM),
- D(ByteOp | DstMem | SrcImplicit | ModRM), D(DstMem | SrcImplicit | ModRM),
+ D(ByteOp | DstMem | ModRM), D(DstMem | ModRM),
N, N, N, N,
/* 0xD8 - 0xDF */
N, N, N, N, N, N, N, N,
/* 0xE0 - 0xE7 */
- N, N, N, N,
- D(ByteOp | SrcImmUByte | DstAcc), D(SrcImmUByte | DstAcc),
+ X4(D(SrcImmByte)),
D(ByteOp | SrcImmUByte | DstAcc), D(SrcImmUByte | DstAcc),
+ D(ByteOp | SrcAcc | DstImmUByte), D(SrcAcc | DstImmUByte),
/* 0xE8 - 0xEF */
D(SrcImm | Stack), D(SrcImm | ImplicitOps),
D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps),
D(SrcNone | ByteOp | DstAcc), D(SrcNone | DstAcc),
- D(SrcNone | ByteOp | DstAcc), D(SrcNone | DstAcc),
+ D(ByteOp | SrcAcc | ImplicitOps), D(SrcAcc | ImplicitOps),
/* 0xF0 - 0xF7 */
N, N, N, N,
D(ImplicitOps | Priv), D(ImplicitOps), G(ByteOp, group3), G(0, group3),
N, N, N, N,
N, N, N, N, N, N, N, N,
/* 0x30 - 0x3F */
- D(ImplicitOps | Priv), N, D(ImplicitOps | Priv), N,
+ D(ImplicitOps | Priv), I(ImplicitOps, em_rdtsc),
+ D(ImplicitOps | Priv), N,
D(ImplicitOps), D(ImplicitOps | Priv), N, N,
N, N, N, N, N, N, N, N,
/* 0x40 - 0x4F */
/* 0x80 - 0x8F */
X16(D(SrcImm)),
/* 0x90 - 0x9F */
- N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N,
+ X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
/* 0xA0 - 0xA7 */
D(ImplicitOps | Stack), D(ImplicitOps | Stack),
N, D(DstMem | SrcReg | ModRM | BitOp),
N, D(DstMem | SrcReg | ModRM | BitOp | Lock),
D(DstMem | SrcReg | Src2ImmByte | ModRM),
D(DstMem | SrcReg | Src2CL | ModRM),
- D(ModRM), N,
+ D(ModRM), I(DstReg | SrcMem | ModRM, em_imul),
/* 0xB0 - 0xB7 */
D(ByteOp | DstMem | SrcReg | ModRM | Lock), D(DstMem | SrcReg | ModRM | Lock),
- N, D(DstMem | SrcReg | ModRM | BitOp | Lock),
- N, N, D(ByteOp | DstReg | SrcMem | ModRM | Mov),
- D(DstReg | SrcMem16 | ModRM | Mov),
+ D(DstReg | SrcMemFAddr | ModRM), D(DstMem | SrcReg | ModRM | BitOp | Lock),
+ D(DstReg | SrcMemFAddr | ModRM), D(DstReg | SrcMemFAddr | ModRM),
+ D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xB8 - 0xBF */
N, N,
G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock),
- N, N, D(ByteOp | DstReg | SrcMem | ModRM | Mov),
- D(DstReg | SrcMem16 | ModRM | Mov),
+ D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM),
+ D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xC0 - 0xCF */
- N, N, N, D(DstMem | SrcReg | ModRM | Mov),
+ D(ByteOp | DstMem | SrcReg | ModRM | Lock), D(DstMem | SrcReg | ModRM | Lock),
+ N, D(DstMem | SrcReg | ModRM | Mov),
N, N, N, GD(0, &group9),
N, N, N, N, N, N, N, N,
/* 0xD0 - 0xDF */
#undef GD
#undef I
+static unsigned imm_size(struct decode_cache *c)
+{
+ unsigned size;
+
+ size = (c->d & ByteOp) ? 1 : c->op_bytes;
+ if (size == 8)
+ size = 4;
+ return size;
+}
+
+static int decode_imm(struct x86_emulate_ctxt *ctxt, struct operand *op,
+ unsigned size, bool sign_extension)
+{
+ struct decode_cache *c = &ctxt->decode;
+ struct x86_emulate_ops *ops = ctxt->ops;
+ int rc = X86EMUL_CONTINUE;
+
+ op->type = OP_IMM;
+ op->bytes = size;
+ op->addr.mem = c->eip;
+ /* NB. Immediates are sign-extended as necessary. */
+ switch (op->bytes) {
+ case 1:
+ op->val = insn_fetch(s8, 1, c->eip);
+ break;
+ case 2:
+ op->val = insn_fetch(s16, 2, c->eip);
+ break;
+ case 4:
+ op->val = insn_fetch(s32, 4, c->eip);
+ break;
+ }
+ if (!sign_extension) {
+ switch (op->bytes) {
+ case 1:
+ op->val &= 0xff;
+ break;
+ case 2:
+ op->val &= 0xffff;
+ break;
+ case 4:
+ op->val &= 0xffffffff;
+ break;
+ }
+ }
+done:
+ return rc;
+}
+
int
x86_decode_insn(struct x86_emulate_ctxt *ctxt)
{
srcmem_common:
c->src = memop;
break;
+ case SrcImmU16:
+ rc = decode_imm(ctxt, &c->src, 2, false);
+ break;
case SrcImm:
+ rc = decode_imm(ctxt, &c->src, imm_size(c), true);
+ break;
case SrcImmU:
- c->src.type = OP_IMM;
- c->src.addr.mem = c->eip;
- c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;
- if (c->src.bytes == 8)
- c->src.bytes = 4;
- /* NB. Immediates are sign-extended as necessary. */
- switch (c->src.bytes) {
- case 1:
- c->src.val = insn_fetch(s8, 1, c->eip);
- break;
- case 2:
- c->src.val = insn_fetch(s16, 2, c->eip);
- break;
- case 4:
- c->src.val = insn_fetch(s32, 4, c->eip);
- break;
- }
- if ((c->d & SrcMask) == SrcImmU) {
- switch (c->src.bytes) {
- case 1:
- c->src.val &= 0xff;
- break;
- case 2:
- c->src.val &= 0xffff;
- break;
- case 4:
- c->src.val &= 0xffffffff;
- break;
- }
- }
+ rc = decode_imm(ctxt, &c->src, imm_size(c), false);
break;
case SrcImmByte:
+ rc = decode_imm(ctxt, &c->src, 1, true);
+ break;
case SrcImmUByte:
- c->src.type = OP_IMM;
- c->src.addr.mem = c->eip;
- c->src.bytes = 1;
- if ((c->d & SrcMask) == SrcImmByte)
- c->src.val = insn_fetch(s8, 1, c->eip);
- else
- c->src.val = insn_fetch(u8, 1, c->eip);
+ rc = decode_imm(ctxt, &c->src, 1, false);
break;
case SrcAcc:
c->src.type = OP_REG;
break;
}
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+
/*
* Decode and fetch the second source operand: register, memory
* or immediate.
c->src2.val = c->regs[VCPU_REGS_RCX] & 0x8;
break;
case Src2ImmByte:
- c->src2.type = OP_IMM;
- c->src2.addr.mem = c->eip;
- c->src2.bytes = 1;
- c->src2.val = insn_fetch(u8, 1, c->eip);
+ rc = decode_imm(ctxt, &c->src2, 1, true);
break;
case Src2One:
c->src2.bytes = 1;
c->src2.val = 1;
break;
+ case Src2Imm:
+ rc = decode_imm(ctxt, &c->src2, imm_size(c), true);
+ break;
}
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+
/* Decode and fetch the destination operand: register or memory. */
switch (c->d & DstMask) {
case DstReg:
decode_register_operand(&c->dst, c,
c->twobyte && (c->b == 0xb6 || c->b == 0xb7));
break;
+ case DstImmUByte:
+ c->dst.type = OP_IMM;
+ c->dst.addr.mem = c->eip;
+ c->dst.bytes = 1;
+ c->dst.val = insn_fetch(u8, 1, c->eip);
+ break;
case DstMem:
case DstMem64:
c->dst = memop;
ctxt->restart = true;
/* All REP prefixes have the same first termination condition */
if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0) {
- string_done:
ctxt->restart = false;
ctxt->eip = c->eip;
goto done;
}
- /* The second termination condition only applies for REPE
- * and REPNE. Test if the repeat string operation prefix is
- * REPE/REPZ or REPNE/REPNZ and if it's the case it tests the
- * corresponding termination condition according to:
- * - if REPE/REPZ and ZF = 0 then done
- * - if REPNE/REPNZ and ZF = 1 then done
- */
- if ((c->b == 0xa6) || (c->b == 0xa7) ||
- (c->b == 0xae) || (c->b == 0xaf)) {
- if ((c->rep_prefix == REPE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == 0))
- goto string_done;
- if ((c->rep_prefix == REPNE_PREFIX) &&
- ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))
- goto string_done;
- }
- c->eip = ctxt->eip;
}
- if (c->src.type == OP_MEM) {
- if (c->d & NoAccess)
- goto no_fetch;
+ if ((c->src.type == OP_MEM) && !(c->d & NoAccess)) {
rc = read_emulated(ctxt, ops, c->src.addr.mem,
c->src.valptr, c->src.bytes);
if (rc != X86EMUL_CONTINUE)
goto done;
c->src.orig_val64 = c->src.val64;
- no_fetch:
- ;
}
if (c->src2.type == OP_MEM) {
break;
case 0x6c: /* insb */
case 0x6d: /* insw/insd */
- c->dst.bytes = min(c->dst.bytes, 4u);
- if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
- c->dst.bytes)) {
- emulate_gp(ctxt, 0);
- goto done;
- }
- if (!pio_in_emulated(ctxt, ops, c->dst.bytes,
- c->regs[VCPU_REGS_RDX], &c->dst.val))
- goto done; /* IO is needed, skip writeback */
- break;
+ c->src.val = c->regs[VCPU_REGS_RDX];
+ goto do_io_in;
case 0x6e: /* outsb */
case 0x6f: /* outsw/outsd */
- c->src.bytes = min(c->src.bytes, 4u);
- if (!emulator_io_permited(ctxt, ops, c->regs[VCPU_REGS_RDX],
- c->src.bytes)) {
- emulate_gp(ctxt, 0);
- goto done;
- }
- ops->pio_out_emulated(c->src.bytes, c->regs[VCPU_REGS_RDX],
- &c->src.val, 1, ctxt->vcpu);
-
- c->dst.type = OP_NONE; /* nothing to writeback */
+ c->dst.val = c->regs[VCPU_REGS_RDX];
+ goto do_io_out;
break;
case 0x70 ... 0x7f: /* jcc (short) */
if (test_cc(c->b, ctxt->eflags))
case 0x86 ... 0x87: /* xchg */
xchg:
/* Write back the register source. */
- switch (c->dst.bytes) {
- case 1:
- *(u8 *) c->src.addr.reg = (u8) c->dst.val;
- break;
- case 2:
- *(u16 *) c->src.addr.reg = (u16) c->dst.val;
- break;
- case 4:
- *c->src.addr.reg = (u32) c->dst.val;
- break; /* 64b reg: zero-extend */
- case 8:
- *c->src.addr.reg = c->dst.val;
- break;
- }
+ c->src.val = c->dst.val;
+ write_register_operand(&c->src);
/*
* Write back the memory destination with implicit LOCK
* prefix.
*/
- c->dst.val = c->src.val;
+ c->dst.val = c->src.orig_val;
c->lock_prefix = 1;
break;
case 0x88 ... 0x8b: /* mov */
if (c->dst.addr.reg == &c->regs[VCPU_REGS_RAX])
break;
goto xchg;
+ case 0x98: /* cbw/cwde/cdqe */
+ switch (c->op_bytes) {
+ case 2: c->dst.val = (s8)c->dst.val; break;
+ case 4: c->dst.val = (s16)c->dst.val; break;
+ case 8: c->dst.val = (s32)c->dst.val; break;
+ }
+ break;
case 0x9c: /* pushf */
c->src.val = (unsigned long) ctxt->eflags;
emulate_push(ctxt, ops);
case 0xac ... 0xad: /* lods */
goto mov;
case 0xae ... 0xaf: /* scas */
- DPRINTF("Urk! I don't handle SCAS.\n");
- goto cannot_emulate;
+ goto cmp;
case 0xb0 ... 0xbf: /* mov r, imm */
goto mov;
case 0xc0 ... 0xc1:
c->dst.addr.reg = &c->eip;
c->dst.bytes = c->op_bytes;
goto pop_instruction;
+ case 0xc4: /* les */
+ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_ES);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ break;
+ case 0xc5: /* lds */
+ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_DS);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ break;
case 0xc6 ... 0xc7: /* mov (sole member of Grp11) */
mov:
c->dst.val = c->src.val;
c->src.val = c->regs[VCPU_REGS_RCX];
emulate_grp2(ctxt);
break;
+ case 0xe0 ... 0xe2: /* loop/loopz/loopnz */
+ register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+ if (address_mask(c, c->regs[VCPU_REGS_RCX]) != 0 &&
+ (c->b == 0xe2 || test_cc(c->b ^ 0x5, ctxt->eflags)))
+ jmp_rel(c, c->src.val);
+ break;
+ case 0xe3: /* jcxz/jecxz/jrcxz */
+ if (address_mask(c, c->regs[VCPU_REGS_RCX]) == 0)
+ jmp_rel(c, c->src.val);
+ break;
case 0xe4: /* inb */
case 0xe5: /* in */
goto do_io_in;
break;
case 0xee: /* out dx,al */
case 0xef: /* out dx,(e/r)ax */
- c->src.val = c->regs[VCPU_REGS_RDX];
+ c->dst.val = c->regs[VCPU_REGS_RDX];
do_io_out:
- c->dst.bytes = min(c->dst.bytes, 4u);
- if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
+ c->src.bytes = min(c->src.bytes, 4u);
+ if (!emulator_io_permited(ctxt, ops, c->dst.val,
+ c->src.bytes)) {
emulate_gp(ctxt, 0);
goto done;
}
- ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1,
- ctxt->vcpu);
+ ops->pio_out_emulated(c->src.bytes, c->dst.val,
+ &c->src.val, 1, ctxt->vcpu);
c->dst.type = OP_NONE; /* Disable writeback. */
break;
case 0xf4: /* hlt */
if (c->rep_prefix && (c->d & String)) {
struct read_cache *rc = &ctxt->decode.io_read;
register_address_increment(c, &c->regs[VCPU_REGS_RCX], -1);
+ /* The second termination condition only applies for REPE
+ * and REPNE. Test if the repeat string operation prefix is
+ * REPE/REPZ or REPNE/REPNZ and if it's the case it tests the
+ * corresponding termination condition according to:
+ * - if REPE/REPZ and ZF = 0 then done
+ * - if REPNE/REPNZ and ZF = 1 then done
+ */
+ if (((c->b == 0xa6) || (c->b == 0xa7) ||
+ (c->b == 0xae) || (c->b == 0xaf))
+ && (((c->rep_prefix == REPE_PREFIX) &&
+ ((ctxt->eflags & EFLG_ZF) == 0))
+ || ((c->rep_prefix == REPNE_PREFIX) &&
+ ((ctxt->eflags & EFLG_ZF) == EFLG_ZF))))
+ ctxt->restart = false;
/*
* Re-enter guest when pio read ahead buffer is empty or,
* if it is not used, after each 1024 iteration.
*/
- if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) ||
- (rc->end != 0 && rc->end == rc->pos))
+ else if ((rc->end == 0 && !(c->regs[VCPU_REGS_RCX] & 0x3ff)) ||
+ (rc->end != 0 && rc->end == rc->pos)) {
ctxt->restart = false;
+ c->eip = ctxt->eip;
+ }
}
/*
* reset read cache here in case string instruction is restared
* without decoding
*/
ctxt->decode.mem_read.end = 0;
- ctxt->eip = c->eip;
+ if (!ctxt->restart)
+ ctxt->eip = c->eip;
done:
return (rc == X86EMUL_UNHANDLEABLE) ? -1 : 0;
if (test_cc(c->b, ctxt->eflags))
jmp_rel(c, c->src.val);
break;
+ case 0x90 ... 0x9f: /* setcc r/m8 */
+ c->dst.val = test_cc(c->b, ctxt->eflags);
+ break;
case 0xa0: /* push fs */
emulate_push_sreg(ctxt, ops, VCPU_SREG_FS);
break;
c->dst.addr.reg = (unsigned long *)&c->regs[VCPU_REGS_RAX];
}
break;
+ case 0xb2: /* lss */
+ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_SS);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ break;
case 0xb3:
btr: /* btr */
emulate_2op_SrcV_nobyte("btr", c->src, c->dst, ctxt->eflags);
break;
+ case 0xb4: /* lfs */
+ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_FS);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ break;
+ case 0xb5: /* lgs */
+ rc = emulate_load_segment(ctxt, ops, VCPU_SREG_GS);
+ if (rc != X86EMUL_CONTINUE)
+ goto done;
+ break;
case 0xb6 ... 0xb7: /* movzx */
c->dst.bytes = c->op_bytes;
c->dst.val = (c->d & ByteOp) ? (u8) c->src.val
btc: /* btc */
emulate_2op_SrcV_nobyte("btc", c->src, c->dst, ctxt->eflags);
break;
+ case 0xbc: { /* bsf */
+ u8 zf;
+ __asm__ ("bsf %2, %0; setz %1"
+ : "=r"(c->dst.val), "=q"(zf)
+ : "r"(c->src.val));
+ ctxt->eflags &= ~X86_EFLAGS_ZF;
+ if (zf) {
+ ctxt->eflags |= X86_EFLAGS_ZF;
+ c->dst.type = OP_NONE; /* Disable writeback. */
+ }
+ break;
+ }
+ case 0xbd: { /* bsr */
+ u8 zf;
+ __asm__ ("bsr %2, %0; setz %1"
+ : "=r"(c->dst.val), "=q"(zf)
+ : "r"(c->src.val));
+ ctxt->eflags &= ~X86_EFLAGS_ZF;
+ if (zf) {
+ ctxt->eflags |= X86_EFLAGS_ZF;
+ c->dst.type = OP_NONE; /* Disable writeback. */
+ }
+ break;
+ }
case 0xbe ... 0xbf: /* movsx */
c->dst.bytes = c->op_bytes;
c->dst.val = (c->d & ByteOp) ? (s8) c->src.val :
(s16) c->src.val;
break;
+ case 0xc0 ... 0xc1: /* xadd */
+ emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags);
+ /* Write back the register source. */
+ c->src.val = c->dst.orig_val;
+ write_register_operand(&c->src);
+ break;
case 0xc3: /* movnti */
c->dst.bytes = c->op_bytes;
c->dst.val = (c->op_bytes == 4) ? (u32) c->src.val :