translate.c

/*
 *  ARM translation
 *
 *  Copyright (c) 2003 Fabrice Bellard
 *  Copyright (c) 2005-2007 CodeSourcery
 *  Copyright (c) 2007 OpenedHand, Ltd.
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include <stdarg.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <inttypes.h>

#include "cpu.h"
#include "exec-all.h"
#include "disas.h"
#include "tcg-op.h"
#include "qemu-log.h"

#include "helpers.h"
#define GEN_HELPER 1
#include "helpers.h"

#define ENABLE_ARCH_5J    0
#define ENABLE_ARCH_6     arm_feature(env, ARM_FEATURE_V6)
#define ENABLE_ARCH_6K   arm_feature(env, ARM_FEATURE_V6K)
#define ENABLE_ARCH_6T2   arm_feature(env, ARM_FEATURE_THUMB2)
#define ENABLE_ARCH_7     arm_feature(env, ARM_FEATURE_V7)

#define ARCH(x) do { if (!ENABLE_ARCH_##x) goto illegal_op; } while(0)

/* internal defines */
typedef struct DisasContext {
    target_ulong pc;
    int is_jmp;
    /* Nonzero if this instruction has been conditionally skipped.  */
    int condjmp;
    /* The label that will be jumped to when the instruction is skipped.  */
    int condlabel;
    /* Thumb-2 condtional execution bits.  */
    int condexec_mask;
    int condexec_cond;
    struct TranslationBlock *tb;
    int singlestep_enabled;
    int thumb;
#if !defined(CONFIG_USER_ONLY)
    int user;
#endif
} DisasContext;

#if defined(CONFIG_USER_ONLY)
#define IS_USER(s) 1
#else
#define IS_USER(s) (s->user)
#endif

/* These instructions trap after executing, so defer them until after the
   conditional executions state has been updated.  */
#define DISAS_WFI 4
#define DISAS_SWI 5

static TCGv_ptr cpu_env;
/* We reuse the same 64-bit temporaries for efficiency.  */
static TCGv_i64 cpu_V0, cpu_V1, cpu_M0;
static TCGv_i32 cpu_R[16];
static TCGv_i32 cpu_exclusive_addr;
static TCGv_i32 cpu_exclusive_val;
static TCGv_i32 cpu_exclusive_high;
#ifdef CONFIG_USER_ONLY
static TCGv_i32 cpu_exclusive_test;
static TCGv_i32 cpu_exclusive_info;
#endif

/* FIXME:  These should be removed.  */
static TCGv cpu_F0s, cpu_F1s;
static TCGv_i64 cpu_F0d, cpu_F1d;

#include "gen-icount.h"

static const char *regnames[] =
    { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7",
      "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" };

/* initialize TCG globals.  */
void arm_translate_init(void)
{
    int i;

    cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");

    for (i = 0; i < 16; i++) {
        cpu_R[i] = tcg_global_mem_new_i32(TCG_AREG0,
                                          offsetof(CPUState, regs[i]),
                                          regnames[i]);
    }
    cpu_exclusive_addr = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUState, exclusive_addr), "exclusive_addr");
    cpu_exclusive_val = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUState, exclusive_val), "exclusive_val");
    cpu_exclusive_high = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUState, exclusive_high), "exclusive_high");
#ifdef CONFIG_USER_ONLY
    cpu_exclusive_test = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUState, exclusive_test), "exclusive_test");
    cpu_exclusive_info = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUState, exclusive_info), "exclusive_info");
#endif

#define GEN_HELPER 2
#include "helpers.h"
}

static int num_temps;

/* Allocate a temporary variable.  */
static TCGv_i32 new_tmp(void)
{
    num_temps++;
    return tcg_temp_new_i32();
}

/* Release a temporary variable.  */
static void dead_tmp(TCGv tmp)
{
    tcg_temp_free(tmp);
    num_temps--;
}

static inline TCGv load_cpu_offset(int offset)
{
    TCGv tmp = new_tmp();
    tcg_gen_ld_i32(tmp, cpu_env, offset);
    return tmp;
}

#define load_cpu_field(name) load_cpu_offset(offsetof(CPUState, name))

static inline void store_cpu_offset(TCGv var, int offset)
{
    tcg_gen_st_i32(var, cpu_env, offset);
    dead_tmp(var);
}

#define store_cpu_field(var, name) \
    store_cpu_offset(var, offsetof(CPUState, name))

/* Set a variable to the value of a CPU register.  */
static void load_reg_var(DisasContext *s, TCGv var, int reg)
{
    if (reg == 15) {
        uint32_t addr;
        /* normaly, since we updated PC, we need only to add one insn */
        if (s->thumb)
            addr = (long)s->pc + 2;
        else
            addr = (long)s->pc + 4;
        tcg_gen_movi_i32(var, addr);
    } else {
        tcg_gen_mov_i32(var, cpu_R[reg]);
    }
}

/* Create a new temporary and set it to the value of a CPU register.  */
static inline TCGv load_reg(DisasContext *s, int reg)
{
    TCGv tmp = new_tmp();
    load_reg_var(s, tmp, reg);
    return tmp;
}

/* Set a CPU register.  The source must be a temporary and will be
   marked as dead.  */
static void store_reg(DisasContext *s, int reg, TCGv var)
{
    if (reg == 15) {
        tcg_gen_andi_i32(var, var, ~1);
        s->is_jmp = DISAS_JUMP;
    }
    tcg_gen_mov_i32(cpu_R[reg], var);
    dead_tmp(var);
}

/* Value extensions.  */
#define gen_uxtb(var) tcg_gen_ext8u_i32(var, var)
#define gen_uxth(var) tcg_gen_ext16u_i32(var, var)
#define gen_sxtb(var) tcg_gen_ext8s_i32(var, var)
#define gen_sxth(var) tcg_gen_ext16s_i32(var, var)

#define gen_sxtb16(var) gen_helper_sxtb16(var, var)
#define gen_uxtb16(var) gen_helper_uxtb16(var, var)


static inline void gen_set_cpsr(TCGv var, uint32_t mask)
{
    TCGv tmp_mask = tcg_const_i32(mask);
    gen_helper_cpsr_write(var, tmp_mask);
    tcg_temp_free_i32(tmp_mask);
}
/* Set NZCV flags from the high 4 bits of var.  */
#define gen_set_nzcv(var) gen_set_cpsr(var, CPSR_NZCV)

static void gen_exception(int excp)
{
    TCGv tmp = new_tmp();
    tcg_gen_movi_i32(tmp, excp);
    gen_helper_exception(tmp);
    dead_tmp(tmp);
}

static void gen_smul_dual(TCGv a, TCGv b)
{
    TCGv tmp1 = new_tmp();
    TCGv tmp2 = new_tmp();
    tcg_gen_ext16s_i32(tmp1, a);
    tcg_gen_ext16s_i32(tmp2, b);
    tcg_gen_mul_i32(tmp1, tmp1, tmp2);
    dead_tmp(tmp2);
    tcg_gen_sari_i32(a, a, 16);
    tcg_gen_sari_i32(b, b, 16);
    tcg_gen_mul_i32(b, b, a);
    tcg_gen_mov_i32(a, tmp1);
    dead_tmp(tmp1);
}

/* Byteswap each halfword.  */
static void gen_rev16(TCGv var)
{
    TCGv tmp = new_tmp();
    tcg_gen_shri_i32(tmp, var, 8);
    tcg_gen_andi_i32(tmp, tmp, 0x00ff00ff);
    tcg_gen_shli_i32(var, var, 8);
    tcg_gen_andi_i32(var, var, 0xff00ff00);
    tcg_gen_or_i32(var, var, tmp);
    dead_tmp(tmp);
}

/* Byteswap low halfword and sign extend.  */
static void gen_revsh(TCGv var)
{
    TCGv tmp = new_tmp();
    tcg_gen_shri_i32(tmp, var, 8);
    tcg_gen_andi_i32(tmp, tmp, 0x00ff);
    tcg_gen_shli_i32(var, var, 8);
    tcg_gen_ext8s_i32(var, var);
    tcg_gen_or_i32(var, var, tmp);
    dead_tmp(tmp);
}

/* Unsigned bitfield extract.  */
static void gen_ubfx(TCGv var, int shift, uint32_t mask)
{
    if (shift)
        tcg_gen_shri_i32(var, var, shift);
    tcg_gen_andi_i32(var, var, mask);
}

/* Signed bitfield extract.  */
static void gen_sbfx(TCGv var, int shift, int width)
{
    uint32_t signbit;

    if (shift)
        tcg_gen_sari_i32(var, var, shift);
    if (shift + width < 32) {
        signbit = 1u << (width - 1);
        tcg_gen_andi_i32(var, var, (1u << width) - 1);
        tcg_gen_xori_i32(var, var, signbit);
        tcg_gen_subi_i32(var, var, signbit);
    }
}

/* Bitfield insertion.  Insert val into base.  Clobbers base and val.  */
static void gen_bfi(TCGv dest, TCGv base, TCGv val, int shift, uint32_t mask)
{
    tcg_gen_andi_i32(val, val, mask);
    tcg_gen_shli_i32(val, val, shift);
    tcg_gen_andi_i32(base, base, ~(mask << shift));
    tcg_gen_or_i32(dest, base, val);
}

/* Round the top 32 bits of a 64-bit value.  */
static void gen_roundqd(TCGv a, TCGv b)
{
    tcg_gen_shri_i32(a, a, 31);
    tcg_gen_add_i32(a, a, b);
}

/* FIXME: Most targets have native widening multiplication.
   It would be good to use that instead of a full wide multiply.  */
/* 32x32->64 multiply.  Marks inputs as dead.  */
static TCGv_i64 gen_mulu_i64_i32(TCGv a, TCGv b)
{
    TCGv_i64 tmp1 = tcg_temp_new_i64();
    TCGv_i64 tmp2 = tcg_temp_new_i64();

    tcg_gen_extu_i32_i64(tmp1, a);
    dead_tmp(a);
    tcg_gen_extu_i32_i64(tmp2, b);
    dead_tmp(b);
    tcg_gen_mul_i64(tmp1, tmp1, tmp2);
    tcg_temp_free_i64(tmp2);
    return tmp1;
}

static TCGv_i64 gen_muls_i64_i32(TCGv a, TCGv b)
{
    TCGv_i64 tmp1 = tcg_temp_new_i64();
    TCGv_i64 tmp2 = tcg_temp_new_i64();

    tcg_gen_ext_i32_i64(tmp1, a);
    dead_tmp(a);
    tcg_gen_ext_i32_i64(tmp2, b);
    dead_tmp(b);
    tcg_gen_mul_i64(tmp1, tmp1, tmp2);
    tcg_temp_free_i64(tmp2);
    return tmp1;
}

/* Signed 32x32->64 multiply.  */
static void gen_imull(TCGv a, TCGv b)
{
    TCGv_i64 tmp1 = tcg_temp_new_i64();
    TCGv_i64 tmp2 = tcg_temp_new_i64();

    tcg_gen_ext_i32_i64(tmp1, a);
    tcg_gen_ext_i32_i64(tmp2, b);
    tcg_gen_mul_i64(tmp1, tmp1, tmp2);
    tcg_temp_free_i64(tmp2);
    tcg_gen_trunc_i64_i32(a, tmp1);
    tcg_gen_shri_i64(tmp1, tmp1, 32);
    tcg_gen_trunc_i64_i32(b, tmp1);
    tcg_temp_free_i64(tmp1);
}

/* Swap low and high halfwords.  */
static void gen_swap_half(TCGv var)
{
    TCGv tmp = new_tmp();
    tcg_gen_shri_i32(tmp, var, 16);
    tcg_gen_shli_i32(var, var, 16);
    tcg_gen_or_i32(var, var, tmp);
    dead_tmp(tmp);
}

/* Dual 16-bit add.  Result placed in t0 and t1 is marked as dead.
    tmp = (t0 ^ t1) & 0x8000;
    t0 &= ~0x8000;
    t1 &= ~0x8000;
    t0 = (t0 + t1) ^ tmp;
 */

static void gen_add16(TCGv t0, TCGv t1)
{
    TCGv tmp = new_tmp();
    tcg_gen_xor_i32(tmp, t0, t1);
    tcg_gen_andi_i32(tmp, tmp, 0x8000);
    tcg_gen_andi_i32(t0, t0, ~0x8000);
    tcg_gen_andi_i32(t1, t1, ~0x8000);
    tcg_gen_add_i32(t0, t0, t1);
    tcg_gen_xor_i32(t0, t0, tmp);
    dead_tmp(tmp);
    dead_tmp(t1);
}

#define gen_set_CF(var) tcg_gen_st_i32(var, cpu_env, offsetof(CPUState, CF))

/* Set CF to the top bit of var.  */
static void gen_set_CF_bit31(TCGv var)
{
    TCGv tmp = new_tmp();
    tcg_gen_shri_i32(tmp, var, 31);
    gen_set_CF(tmp);
    dead_tmp(tmp);
}

/* Set N and Z flags from var.  */
static inline void gen_logic_CC(TCGv var)
{
    tcg_gen_st_i32(var, cpu_env, offsetof(CPUState, NF));
    tcg_gen_st_i32(var, cpu_env, offsetof(CPUState, ZF));
}

/* T0 += T1 + CF.  */
static void gen_adc(TCGv t0, TCGv t1)
{
    TCGv tmp;
    tcg_gen_add_i32(t0, t0, t1);
    tmp = load_cpu_field(CF);
    tcg_gen_add_i32(t0, t0, tmp);
    dead_tmp(tmp);
}

/* dest = T0 + T1 + CF. */
static void gen_add_carry(TCGv dest, TCGv t0, TCGv t1)
{
    TCGv tmp;
    tcg_gen_add_i32(dest, t0, t1);
    tmp = load_cpu_field(CF);
    tcg_gen_add_i32(dest, dest, tmp);
    dead_tmp(tmp);
}

/* dest = T0 - T1 + CF - 1.  */
static void gen_sub_carry(TCGv dest, TCGv t0, TCGv t1)
{
    TCGv tmp;
    tcg_gen_sub_i32(dest, t0, t1);
    tmp = load_cpu_field(CF);
    tcg_gen_add_i32(dest, dest, tmp);
    tcg_gen_subi_i32(dest, dest, 1);
    dead_tmp(tmp);
}

/* FIXME:  Implement this natively.  */
#define tcg_gen_abs_i32(t0, t1) gen_helper_abs(t0, t1)

static void shifter_out_im(TCGv var, int shift)
{
    TCGv tmp = new_tmp();
    if (shift == 0) {
        tcg_gen_andi_i32(tmp, var, 1);
    } else {
        tcg_gen_shri_i32(tmp, var, shift);
        if (shift != 31)
            tcg_gen_andi_i32(tmp, tmp, 1);
    }
    gen_set_CF(tmp);
    dead_tmp(tmp);
}

/* Shift by immediate.  Includes special handling for shift == 0.  */
static inline void gen_arm_shift_im(TCGv var, int shiftop, int shift, int flags)
{
    switch (shiftop) {
    case 0: /* LSL */
        if (shift != 0) {
            if (flags)
                shifter_out_im(var, 32 - shift);
            tcg_gen_shli_i32(var, var, shift);
        }
        break;
    case 1: /* LSR */
        if (shift == 0) {
            if (flags) {
                tcg_gen_shri_i32(var, var, 31);
                gen_set_CF(var);
            }
            tcg_gen_movi_i32(var, 0);
        } else {
            if (flags)
                shifter_out_im(var, shift - 1);
            tcg_gen_shri_i32(var, var, shift);
        }
        break;
    case 2: /* ASR */
        if (shift == 0)
            shift = 32;
        if (flags)
            shifter_out_im(var, shift - 1);
        if (shift == 32)
          shift = 31;
        tcg_gen_sari_i32(var, var, shift);
        break;
    case 3: /* ROR/RRX */
        if (shift != 0) {
            if (flags)
                shifter_out_im(var, shift - 1);
            tcg_gen_rotri_i32(var, var, shift); break;
        } else {
            TCGv tmp = load_cpu_field(CF);
            if (flags)
                shifter_out_im(var, 0);
            tcg_gen_shri_i32(var, var, 1);
            tcg_gen_shli_i32(tmp, tmp, 31);
            tcg_gen_or_i32(var, var, tmp);
            dead_tmp(tmp);
        }
    }
};

static inline void gen_arm_shift_reg(TCGv var, int shiftop,
                                     TCGv shift, int flags)
{
    if (flags) {
        switch (shiftop) {
        case 0: gen_helper_shl_cc(var, var, shift); break;
        case 1: gen_helper_shr_cc(var, var, shift); break;
        case 2: gen_helper_sar_cc(var, var, shift); break;
        case 3: gen_helper_ror_cc(var, var, shift); break;
        }
    } else {
        switch (shiftop) {
        case 0: gen_helper_shl(var, var, shift); break;
        case 1: gen_helper_shr(var, var, shift); break;
        case 2: gen_helper_sar(var, var, shift); break;
        case 3: tcg_gen_andi_i32(shift, shift, 0x1f);
                tcg_gen_rotr_i32(var, var, shift); break;
        }
    }
    dead_tmp(shift);
}

#define PAS_OP(pfx) \
    switch (op2) {  \
    case 0: gen_pas_helper(glue(pfx,add16)); break; \
    case 1: gen_pas_helper(glue(pfx,addsubx)); break; \
    case 2: gen_pas_helper(glue(pfx,subaddx)); break; \
    case 3: gen_pas_helper(glue(pfx,sub16)); break; \
    case 4: gen_pas_helper(glue(pfx,add8)); break; \
    case 7: gen_pas_helper(glue(pfx,sub8)); break; \
    }
static void gen_arm_parallel_addsub(int op1, int op2, TCGv a, TCGv b)
{
    TCGv_ptr tmp;

    switch (op1) {
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b, tmp)
    case 1:
        tmp = tcg_temp_new_ptr();
        tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
        PAS_OP(s)
        tcg_temp_free_ptr(tmp);
        break;
    case 5:
        tmp = tcg_temp_new_ptr();
        tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
        PAS_OP(u)
        tcg_temp_free_ptr(tmp);
        break;
#undef gen_pas_helper
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b)
    case 2:
        PAS_OP(q);
        break;
    case 3:
        PAS_OP(sh);
        break;
    case 6:
        PAS_OP(uq);
        break;
    case 7:
        PAS_OP(uh);
        break;
#undef gen_pas_helper
    }
}
#undef PAS_OP

/* For unknown reasons Arm and Thumb-2 use arbitrarily different encodings.  */
#define PAS_OP(pfx) \
    switch (op2) {  \
    case 0: gen_pas_helper(glue(pfx,add8)); break; \
    case 1: gen_pas_helper(glue(pfx,add16)); break; \
    case 2: gen_pas_helper(glue(pfx,addsubx)); break; \
    case 4: gen_pas_helper(glue(pfx,sub8)); break; \
    case 5: gen_pas_helper(glue(pfx,sub16)); break; \
    case 6: gen_pas_helper(glue(pfx,subaddx)); break; \
    }
static void gen_thumb2_parallel_addsub(int op1, int op2, TCGv a, TCGv b)
{
    TCGv_ptr tmp;

    switch (op1) {
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b, tmp)
    case 0:
        tmp = tcg_temp_new_ptr();
        tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
        PAS_OP(s)
        tcg_temp_free_ptr(tmp);
        break;
    case 4:
        tmp = tcg_temp_new_ptr();
        tcg_gen_addi_ptr(tmp, cpu_env, offsetof(CPUState, GE));
        PAS_OP(u)
        tcg_temp_free_ptr(tmp);
        break;
#undef gen_pas_helper
#define gen_pas_helper(name) glue(gen_helper_,name)(a, a, b)
    case 1:
        PAS_OP(q);
        break;
    case 2:
        PAS_OP(sh);
        break;
    case 5:
        PAS_OP(uq);
        break;
    case 6:
        PAS_OP(uh);
        break;
#undef gen_pas_helper
    }
}
#undef PAS_OP

static void gen_test_cc(int cc, int label)
{
    TCGv tmp;
    TCGv tmp2;
    int inv;

    switch (cc) {
    case 0: /* eq: Z */
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
        break;
    case 1: /* ne: !Z */
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
        break;
    case 2: /* cs: C */
        tmp = load_cpu_field(CF);
        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
        break;
    case 3: /* cc: !C */
        tmp = load_cpu_field(CF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
        break;
    case 4: /* mi: N */
        tmp = load_cpu_field(NF);
        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
        break;
    case 5: /* pl: !N */
        tmp = load_cpu_field(NF);
        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
        break;
    case 6: /* vs: V */
        tmp = load_cpu_field(VF);
        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
        break;
    case 7: /* vc: !V */
        tmp = load_cpu_field(VF);
        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
        break;
    case 8: /* hi: C && !Z */
        inv = gen_new_label();
        tmp = load_cpu_field(CF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, inv);
        dead_tmp(tmp);
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_NE, tmp, 0, label);
        gen_set_label(inv);
        break;
    case 9: /* ls: !C || Z */
        tmp = load_cpu_field(CF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
        dead_tmp(tmp);
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
        break;
    case 10: /* ge: N == V -> N ^ V == 0 */
        tmp = load_cpu_field(VF);
        tmp2 = load_cpu_field(NF);
        tcg_gen_xor_i32(tmp, tmp, tmp2);
        dead_tmp(tmp2);
        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
        break;
    case 11: /* lt: N != V -> N ^ V != 0 */
        tmp = load_cpu_field(VF);
        tmp2 = load_cpu_field(NF);
        tcg_gen_xor_i32(tmp, tmp, tmp2);
        dead_tmp(tmp2);
        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
        break;
    case 12: /* gt: !Z && N == V */
        inv = gen_new_label();
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, inv);
        dead_tmp(tmp);
        tmp = load_cpu_field(VF);
        tmp2 = load_cpu_field(NF);
        tcg_gen_xor_i32(tmp, tmp, tmp2);
        dead_tmp(tmp2);
        tcg_gen_brcondi_i32(TCG_COND_GE, tmp, 0, label);
        gen_set_label(inv);
        break;
    case 13: /* le: Z || N != V */
        tmp = load_cpu_field(ZF);
        tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, 0, label);
        dead_tmp(tmp);
        tmp = load_cpu_field(VF);
        tmp2 = load_cpu_field(NF);
        tcg_gen_xor_i32(tmp, tmp, tmp2);
        dead_tmp(tmp2);
        tcg_gen_brcondi_i32(TCG_COND_LT, tmp, 0, label);
        break;
    default:
        fprintf(stderr, "Bad condition code 0x%x\n", cc);
        abort();
    }
    dead_tmp(tmp);
}

static const uint8_t table_logic_cc[16] = {
    1, /* and */
    1, /* xor */
    0, /* sub */
    0, /* rsb */
    0, /* add */
    0, /* adc */
    0, /* sbc */
    0, /* rsc */
    1, /* andl */
    1, /* xorl */
    0, /* cmp */
    0, /* cmn */
    1, /* orr */
    1, /* mov */
    1, /* bic */
    1, /* mvn */
};

/* Set PC and Thumb state from an immediate address.  */
static inline void gen_bx_im(DisasContext *s, uint32_t addr)
{
    TCGv tmp;

    s->is_jmp = DISAS_UPDATE;
    if (s->thumb != (addr & 1)) {
        tmp = new_tmp();
        tcg_gen_movi_i32(tmp, addr & 1);
        tcg_gen_st_i32(tmp, cpu_env, offsetof(CPUState, thumb));
        dead_tmp(tmp);
    }
    tcg_gen_movi_i32(cpu_R[15], addr & ~1);
}

/* Set PC and Thumb state from var.  var is marked as dead.  */
static inline void gen_bx(DisasContext *s, TCGv var)
{
    s->is_jmp = DISAS_UPDATE;
    tcg_gen_andi_i32(cpu_R[15], var, ~1);
    tcg_gen_andi_i32(var, var, 1);
    store_cpu_field(var, thumb);
}

/* Variant of store_reg which uses branch&exchange logic when storing
   to r15 in ARM architecture v7 and above. The source must be a temporary
   and will be marked as dead. */
static inline void store_reg_bx(CPUState *env, DisasContext *s,
                                int reg, TCGv var)
{
    if (reg == 15 && ENABLE_ARCH_7) {
        gen_bx(s, var);
    } else {
        store_reg(s, reg, var);
    }
}

static inline TCGv gen_ld8s(TCGv addr, int index)
{
    TCGv tmp = new_tmp();
    tcg_gen_qemu_ld8s(tmp, addr, index);
    return tmp;
}
static inline TCGv gen_ld8u(TCGv addr, int index)
{
    TCGv tmp = new_tmp();
    tcg_gen_qemu_ld8u(tmp, addr, index);
    return tmp;
}
static inline TCGv gen_ld16s(TCGv addr, int index)
{
    TCGv tmp = new_tmp();
    tcg_gen_qemu_ld16s(tmp, addr, index);
    return tmp;
}
static inline TCGv gen_ld16u(TCGv addr, int index)
{
    TCGv tmp = new_tmp();
    tcg_gen_qemu_ld16u(tmp, addr, index);
    return tmp;
}
static inline TCGv gen_ld32(TCGv addr, int index)
{
    TCGv tmp = new_tmp();
    tcg_gen_qemu_ld32u(tmp, addr, index);
    return tmp;
}
static inline TCGv_i64 gen_ld64(TCGv addr, int index)
{
    TCGv_i64 tmp = tcg_temp_new_i64();
    tcg_gen_qemu_ld64(tmp, addr, index);
    return tmp;
}
static inline void gen_st8(TCGv val, TCGv addr, int index)
{
    tcg_gen_qemu_st8(val, addr, index);
    dead_tmp(val);
}
static inline void gen_st16(TCGv val, TCGv addr, int index)
{
    tcg_gen_qemu_st16(val, addr, index);
    dead_tmp(val);
}
static inline void gen_st32(TCGv val, TCGv addr, int index)
{
    tcg_gen_qemu_st32(val, addr, index);
    dead_tmp(val);
}
static inline void gen_st64(TCGv_i64 val, TCGv addr, int index)
{
    tcg_gen_qemu_st64(val, addr, index);
    tcg_temp_free_i64(val);
}

static inline void gen_set_pc_im(uint32_t val)
{
    tcg_gen_movi_i32(cpu_R[15], val);
}

/* Force a TB lookup after an instruction that changes the CPU state.  */
static inline void gen_lookup_tb(DisasContext *s)
{
    tcg_gen_movi_i32(cpu_R[15], s->pc & ~1);
    s->is_jmp = DISAS_UPDATE;
}

static inline void gen_add_data_offset(DisasContext *s, unsigned int insn,
                                       TCGv var)
{
    int val, rm, shift, shiftop;
    TCGv offset;

    if (!(insn & (1 << 25))) {
        /* immediate */
        val = insn & 0xfff;
        if (!(insn & (1 << 23)))
            val = -val;
        if (val != 0)
            tcg_gen_addi_i32(var, var, val);
    } else {
        /* shift/register */
        rm = (insn) & 0xf;
        shift = (insn >> 7) & 0x1f;
        shiftop = (insn >> 5) & 3;
        offset = load_reg(s, rm);
        gen_arm_shift_im(offset, shiftop, shift, 0);
        if (!(insn & (1 << 23)))
            tcg_gen_sub_i32(var, var, offset);
        else
            tcg_gen_add_i32(var, var, offset);
        dead_tmp(offset);
    }
}

static inline void gen_add_datah_offset(DisasContext *s, unsigned int insn,
                                        int extra, TCGv var)
{
    int val, rm;
    TCGv offset;

    if (insn & (1 << 22)) {
        /* immediate */
        val = (insn & 0xf) | ((insn >> 4) & 0xf0);
        if (!(insn & (1 << 23)))
            val = -val;
        val += extra;
        if (val != 0)
            tcg_gen_addi_i32(var, var, val);
    } else {
        /* register */
        if (extra)
            tcg_gen_addi_i32(var, var, extra);
        rm = (insn) & 0xf;
        offset = load_reg(s, rm);
        if (!(insn & (1 << 23)))
            tcg_gen_sub_i32(var, var, offset);
        else
            tcg_gen_add_i32(var, var, offset);
        dead_tmp(offset);
    }
}

#define VFP_OP2(name)                                                 \
static inline void gen_vfp_##name(int dp)                             \
{                                                                     \
    if (dp)                                                           \
        gen_helper_vfp_##name##d(cpu_F0d, cpu_F0d, cpu_F1d, cpu_env); \
    else                                                              \
        gen_helper_vfp_##name##s(cpu_F0s, cpu_F0s, cpu_F1s, cpu_env); \
}

VFP_OP2(add)
VFP_OP2(sub)
VFP_OP2(mul)
VFP_OP2(div)

#undef VFP_OP2

static inline void gen_vfp_abs(int dp)
{
    if (dp)
        gen_helper_vfp_absd(cpu_F0d, cpu_F0d);
    else
        gen_helper_vfp_abss(cpu_F0s, cpu_F0s);
}

static inline void gen_vfp_neg(int dp)
{
    if (dp)
        gen_helper_vfp_negd(cpu_F0d, cpu_F0d);
    else
        gen_helper_vfp_negs(cpu_F0s, cpu_F0s);
}

static inline void gen_vfp_sqrt(int dp)
{
    if (dp)
        gen_helper_vfp_sqrtd(cpu_F0d, cpu_F0d, cpu_env);
    else
        gen_helper_vfp_sqrts(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_cmp(int dp)
{
    if (dp)
        gen_helper_vfp_cmpd(cpu_F0d, cpu_F1d, cpu_env);
    else
        gen_helper_vfp_cmps(cpu_F0s, cpu_F1s, cpu_env);
}

static inline void gen_vfp_cmpe(int dp)
{
    if (dp)
        gen_helper_vfp_cmped(cpu_F0d, cpu_F1d, cpu_env);
    else
        gen_helper_vfp_cmpes(cpu_F0s, cpu_F1s, cpu_env);
}

static inline void gen_vfp_F1_ld0(int dp)
{
    if (dp)
        tcg_gen_movi_i64(cpu_F1d, 0);
    else
        tcg_gen_movi_i32(cpu_F1s, 0);
}

static inline void gen_vfp_uito(int dp)
{
    if (dp)
        gen_helper_vfp_uitod(cpu_F0d, cpu_F0s, cpu_env);
    else
        gen_helper_vfp_uitos(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_sito(int dp)
{
    if (dp)
        gen_helper_vfp_sitod(cpu_F0d, cpu_F0s, cpu_env);
    else
        gen_helper_vfp_sitos(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_toui(int dp)
{
    if (dp)
        gen_helper_vfp_touid(cpu_F0s, cpu_F0d, cpu_env);
    else
        gen_helper_vfp_touis(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_touiz(int dp)
{
    if (dp)
        gen_helper_vfp_touizd(cpu_F0s, cpu_F0d, cpu_env);
    else
        gen_helper_vfp_touizs(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_tosi(int dp)
{
    if (dp)
        gen_helper_vfp_tosid(cpu_F0s, cpu_F0d, cpu_env);
    else
        gen_helper_vfp_tosis(cpu_F0s, cpu_F0s, cpu_env);
}

static inline void gen_vfp_tosiz(int dp)
{
    if (dp)
        gen_helper_vfp_tosizd(cpu_F0s, cpu_F0d, cpu_env);
    else
        gen_helper_vfp_tosizs(cpu_F0s, cpu_F0s, cpu_env);
}

#define VFP_GEN_FIX(name) \
static inline void gen_vfp_##name(int dp, int shift) \
{ \
    TCGv tmp_shift = tcg_const_i32(shift); \
    if (dp) \
        gen_helper_vfp_##name##d(cpu_F0d, cpu_F0d, tmp_shift, cpu_env);\
    else \
        gen_helper_vfp_##name##s(cpu_F0s, cpu_F0s, tmp_shift, cpu_env);\
    tcg_temp_free_i32(tmp_shift); \
}
VFP_GEN_FIX(tosh)
VFP_GEN_FIX(tosl)
VFP_GEN_FIX(touh)
VFP_GEN_FIX(toul)
VFP_GEN_FIX(shto)
VFP_GEN_FIX(slto)
VFP_GEN_FIX(uhto)
VFP_GEN_FIX(ulto)
#undef VFP_GEN_FIX

static inline void gen_vfp_ld(DisasContext *s, int dp, TCGv addr)
{
    if (dp)
        tcg_gen_qemu_ld64(cpu_F0d, addr, IS_USER(s));
    else
        tcg_gen_qemu_ld32u(cpu_F0s, addr, IS_USER(s));
}

static inline void gen_vfp_st(DisasContext *s, int dp, TCGv addr)
{
    if (dp)
        tcg_gen_qemu_st64(cpu_F0d, addr, IS_USER(s));
    else
        tcg_gen_qemu_st32(cpu_F0s, addr, IS_USER(s));
}

static inline long
vfp_reg_offset (int dp, int reg)
{
    if (dp)
        return offsetof(CPUARMState, vfp.regs[reg]);
    else if (reg & 1) {
        return offsetof(CPUARMState, vfp.regs[reg >> 1])
          + offsetof(CPU_DoubleU, l.upper);
    } else {
        return offsetof(CPUARMState, vfp.regs[reg >> 1])
          + offsetof(CPU_DoubleU, l.lower);
    }
}

/* Return the offset of a 32-bit piece of a NEON register.
   zero is the least significant end of the register.  */
static inline long
neon_reg_offset (int reg, int n)
{
    int sreg;
    sreg = reg * 2 + n;
    return vfp_reg_offset(0, sreg);
}

static TCGv neon_load_reg(int reg, int pass)
{
    TCGv tmp = new_tmp();
    tcg_gen_ld_i32(tmp, cpu_env, neon_reg_offset(reg, pass));
    return tmp;
}

static void neon_store_reg(int reg, int pass, TCGv var)
{
    tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass));
    dead_tmp(var);
}

static inline void neon_load_reg64(TCGv_i64 var, int reg)
{
    tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg));
}

static inline void neon_store_reg64(TCGv_i64 var, int reg)
{
    tcg_gen_st_i64(var, cpu_env, vfp_reg_offset(1, reg));
}

#define tcg_gen_ld_f32 tcg_gen_ld_i32
#define tcg_gen_ld_f64 tcg_gen_ld_i64
#define tcg_gen_st_f32 tcg_gen_st_i32
#define tcg_gen_st_f64 tcg_gen_st_i64

static inline void gen_mov_F0_vreg(int dp, int reg)
{
    if (dp)
        tcg_gen_ld_f64(cpu_F0d, cpu_env, vfp_reg_offset(dp, reg));
    else
        tcg_gen_ld_f32(cpu_F0s, cpu_env, vfp_reg_offset(dp, reg));
}

static inline void gen_mov_F1_vreg(int dp, int reg)
{
    if (dp)
        tcg_gen_ld_f64(cpu_F1d, cpu_env, vfp_reg_offset(dp, reg));
    else
        tcg_gen_ld_f32(cpu_F1s, cpu_env, vfp_reg_offset(dp, reg));
}

static inline void gen_mov_vreg_F0(int dp, int reg)
{
    if (dp)
        tcg_gen_st_f64(cpu_F0d, cpu_env, vfp_reg_offset(dp, reg));
    else
        tcg_gen_st_f32(cpu_F0s, cpu_env, vfp_reg_offset(dp, reg));
}

#define ARM_CP_RW_BIT	(1 << 20)

static inline void iwmmxt_load_reg(TCGv_i64 var, int reg)
{
    tcg_gen_ld_i64(var, cpu_env, offsetof(CPUState, iwmmxt.regs[reg]));
}

static inline void iwmmxt_store_reg(TCGv_i64 var, int reg)
{
    tcg_gen_st_i64(var, cpu_env, offsetof(CPUState, iwmmxt.regs[reg]));
}

static inline TCGv iwmmxt_load_creg(int reg)
{
    TCGv var = new_tmp();
    tcg_gen_ld_i32(var, cpu_env, offsetof(CPUState, iwmmxt.cregs[reg]));
    return var;
}

static inline void iwmmxt_store_creg(int reg, TCGv var)
{
    tcg_gen_st_i32(var, cpu_env, offsetof(CPUState, iwmmxt.cregs[reg]));
    dead_tmp(var);
}

static inline void gen_op_iwmmxt_movq_wRn_M0(int rn)
{
    iwmmxt_store_reg(cpu_M0, rn);
}

static inline void gen_op_iwmmxt_movq_M0_wRn(int rn)
{
    iwmmxt_load_reg(cpu_M0, rn);
}

static inline void gen_op_iwmmxt_orq_M0_wRn(int rn)
{
    iwmmxt_load_reg(cpu_V1, rn);
    tcg_gen_or_i64(cpu_M0, cpu_M0, cpu_V1);
}

static inline void gen_op_iwmmxt_andq_M0_wRn(int rn)
{
    iwmmxt_load_reg(cpu_V1, rn);
    tcg_gen_and_i64(cpu_M0, cpu_M0, cpu_V1);
}

static inline void gen_op_iwmmxt_xorq_M0_wRn(int rn)
{
    iwmmxt_load_reg(cpu_V1, rn);
    tcg_gen_xor_i64(cpu_M0, cpu_M0, cpu_V1);
}

#define IWMMXT_OP(name) \
static inline void gen_op_iwmmxt_##name##_M0_wRn(int rn) \
{ \
    iwmmxt_load_reg(cpu_V1, rn); \
    gen_helper_iwmmxt_##name(cpu_M0, cpu_M0, cpu_V1); \
}

#define IWMMXT_OP_ENV(name) \
static inline void gen_op_iwmmxt_##name##_M0_wRn(int rn) \
{ \
    iwmmxt_load_reg(cpu_V1, rn); \
    gen_helper_iwmmxt_##name(cpu_M0, cpu_env, cpu_M0, cpu_V1); \
}

#define IWMMXT_OP_ENV_SIZE(name) \
IWMMXT_OP_ENV(name##b) \
IWMMXT_OP_ENV(name##w) \
IWMMXT_OP_ENV(name##l)

#define IWMMXT_OP_ENV1(name) \
static inline void gen_op_iwmmxt_##name##_M0(void) \
{ \
    gen_helper_iwmmxt_##name(cpu_M0, cpu_env, cpu_M0); \
}

IWMMXT_OP(maddsq)
IWMMXT_OP(madduq)
IWMMXT_OP(sadb)
IWMMXT_OP(sadw)
IWMMXT_OP(mulslw)
IWMMXT_OP(mulshw)
IWMMXT_OP(mululw)
IWMMXT_OP(muluhw)
IWMMXT_OP(macsw)
IWMMXT_OP(macuw)

IWMMXT_OP_ENV_SIZE(unpackl)
IWMMXT_OP_ENV_SIZE(unpackh)

IWMMXT_OP_ENV1(unpacklub)
IWMMXT_OP_ENV1(unpackluw)
IWMMXT_OP_ENV1(unpacklul)
IWMMXT_OP_ENV1(unpackhub)
IWMMXT_OP_ENV1(unpackhuw)
IWMMXT_OP_ENV1(unpackhul)
IWMMXT_OP_ENV1(unpacklsb)
IWMMXT_OP_ENV1(unpacklsw)
IWMMXT_OP_ENV1(unpacklsl)
IWMMXT_OP_ENV1(unpackhsb)
IWMMXT_OP_ENV1(unpackhsw)
IWMMXT_OP_ENV1(unpackhsl)

IWMMXT_OP_ENV_SIZE(cmpeq)
IWMMXT_OP_ENV_SIZE(cmpgtu)
IWMMXT_OP_ENV_SIZE(cmpgts)

IWMMXT_OP_ENV_SIZE(mins)
IWMMXT_OP_ENV_SIZE(minu)
IWMMXT_OP_ENV_SIZE(maxs)
IWMMXT_OP_ENV_SIZE(maxu)

IWMMXT_OP_ENV_SIZE(subn)
IWMMXT_OP_ENV_SIZE(addn)
IWMMXT_OP_ENV_SIZE(subu)
IWMMXT_OP_ENV_SIZE(addu)
IWMMXT_OP_ENV_SIZE(subs)
IWMMXT_OP_ENV_SIZE(adds)

IWMMXT_OP_ENV(avgb0)
IWMMXT_OP_ENV(avgb1)
IWMMXT_OP_ENV(avgw0)
IWMMXT_OP_ENV(avgw1)

IWMMXT_OP(msadb)

IWMMXT_OP_ENV(packuw)
IWMMXT_OP_ENV(packul)
IWMMXT_OP_ENV(packuq)
IWMMXT_OP_ENV(packsw)
IWMMXT_OP_ENV(packsl)
IWMMXT_OP_ENV(packsq)

static void gen_op_iwmmxt_set_mup(void)
{
    TCGv tmp;
    tmp = load_cpu_field(iwmmxt.cregs[ARM_IWMMXT_wCon]);
    tcg_gen_ori_i32(tmp, tmp, 2);
    store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCon]);
}

static void gen_op_iwmmxt_set_cup(void)
{
    TCGv tmp;
    tmp = load_cpu_field(iwmmxt.cregs[ARM_IWMMXT_wCon]);
    tcg_gen_ori_i32(tmp, tmp, 1);
    store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCon]);
}

static void gen_op_iwmmxt_setpsr_nz(void)
{
    TCGv tmp = new_tmp();
    gen_helper_iwmmxt_setpsr_nz(tmp, cpu_M0);
    store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCASF]);
}

static inline void gen_op_iwmmxt_addl_M0_wRn(int rn)
{
    iwmmxt_load_reg(cpu_V1, rn);
    tcg_gen_ext32u_i64(cpu_V1, cpu_V1);
    tcg_gen_add_i64(cpu_M0, cpu_M0, cpu_V1);
}

static inline int gen_iwmmxt_address(DisasContext *s, uint32_t insn, TCGv dest)
{
    int rd;
    uint32_t offset;
    TCGv tmp;

    rd = (insn >> 16) & 0xf;
    tmp = load_reg(s, rd);

    offset = (insn & 0xff) << ((insn >> 7) & 2);
    if (insn & (1 << 24)) {
        /* Pre indexed */
        if (insn & (1 << 23))
            tcg_gen_addi_i32(tmp, tmp, offset);
        else
            tcg_gen_addi_i32(tmp, tmp, -offset);
        tcg_gen_mov_i32(dest, tmp);
        if (insn & (1 << 21))
            store_reg(s, rd, tmp);
        else
            dead_tmp(tmp);
    } else if (insn & (1 << 21)) {
        /* Post indexed */
        tcg_gen_mov_i32(dest, tmp);
        if (insn & (1 << 23))
            tcg_gen_addi_i32(tmp, tmp, offset);
        else
            tcg_gen_addi_i32(tmp, tmp, -offset);
        store_reg(s, rd, tmp);
    } else if (!(insn & (1 << 23)))
        return 1;
    return 0;
}

static inline int gen_iwmmxt_shift(uint32_t insn, uint32_t mask, TCGv dest)
{
    int rd = (insn >> 0) & 0xf;
    TCGv tmp;

    if (insn & (1 << 8)) {
        if (rd < ARM_IWMMXT_wCGR0 || rd > ARM_IWMMXT_wCGR3) {
            return 1;
        } else {
            tmp = iwmmxt_load_creg(rd);
        }
    } else {
        tmp = new_tmp();
        iwmmxt_load_reg(cpu_V0, rd);
        tcg_gen_trunc_i64_i32(tmp, cpu_V0);
    }
    tcg_gen_andi_i32(tmp, tmp, mask);
    tcg_gen_mov_i32(dest, tmp);
    dead_tmp(tmp);
    return 0;
}

/* Disassemble an iwMMXt instruction.  Returns nonzero if an error occured
   (ie. an undefined instruction).  */
static int disas_iwmmxt_insn(CPUState *env, DisasContext *s, uint32_t insn)
{
    int rd, wrd;
    int rdhi, rdlo, rd0, rd1, i;
    TCGv addr;
    TCGv tmp, tmp2, tmp3;

    if ((insn & 0x0e000e00) == 0x0c000000) {
        if ((insn & 0x0fe00ff0) == 0x0c400000) {
            wrd = insn & 0xf;
            rdlo = (insn >> 12) & 0xf;
            rdhi = (insn >> 16) & 0xf;
            if (insn & ARM_CP_RW_BIT) {			/* TMRRC */
                iwmmxt_load_reg(cpu_V0, wrd);
                tcg_gen_trunc_i64_i32(cpu_R[rdlo], cpu_V0);
                tcg_gen_shri_i64(cpu_V0, cpu_V0, 32);
                tcg_gen_trunc_i64_i32(cpu_R[rdhi], cpu_V0);
            } else {					/* TMCRR */
                tcg_gen_concat_i32_i64(cpu_V0, cpu_R[rdlo], cpu_R[rdhi]);
                iwmmxt_store_reg(cpu_V0, wrd);
                gen_op_iwmmxt_set_mup();
            }
            return 0;
        }

        wrd = (insn >> 12) & 0xf;
        addr = new_tmp();
        if (gen_iwmmxt_address(s, insn, addr)) {
            dead_tmp(addr);
            return 1;
        }
        if (insn & ARM_CP_RW_BIT) {
            if ((insn >> 28) == 0xf) {			/* WLDRW wCx */
                tmp = new_tmp();
                tcg_gen_qemu_ld32u(tmp, addr, IS_USER(s));
                iwmmxt_store_creg(wrd, tmp);
            } else {
                i = 1;
                if (insn & (1 << 8)) {
                    if (insn & (1 << 22)) {		/* WLDRD */
                        tcg_gen_qemu_ld64(cpu_M0, addr, IS_USER(s));
                        i = 0;
                    } else {				/* WLDRW wRd */
                        tmp = gen_ld32(addr, IS_USER(s));
                    }
                } else {
                    if (insn & (1 << 22)) {		/* WLDRH */
                        tmp = gen_ld16u(addr, IS_USER(s));
                    } else {				/* WLDRB */
                        tmp = gen_ld8u(addr, IS_USER(s));
                    }
                }
                if (i) {
                    tcg_gen_extu_i32_i64(cpu_M0, tmp);
                    dead_tmp(tmp);
                }
                gen_op_iwmmxt_movq_wRn_M0(wrd);
            }
        } else {
            if ((insn >> 28) == 0xf) {			/* WSTRW wCx */
                tmp = iwmmxt_load_creg(wrd);
                gen_st32(tmp, addr, IS_USER(s));
            } else {
                gen_op_iwmmxt_movq_M0_wRn(wrd);
                tmp = new_tmp();
                if (insn & (1 << 8)) {
                    if (insn & (1 << 22)) {		/* WSTRD */
                        dead_tmp(tmp);
                        tcg_gen_qemu_st64(cpu_M0, addr, IS_USER(s));
                    } else {				/* WSTRW wRd */
                        tcg_gen_trunc_i64_i32(tmp, cpu_M0);
                        gen_st32(tmp, addr, IS_USER(s));
                    }
                } else {
                    if (insn & (1 << 22)) {		/* WSTRH */
                        tcg_gen_trunc_i64_i32(tmp, cpu_M0);
                        gen_st16(tmp, addr, IS_USER(s));
                    } else {				/* WSTRB */
                        tcg_gen_trunc_i64_i32(tmp, cpu_M0);
                        gen_st8(tmp, addr, IS_USER(s));
                    }
                }
            }
        }
        dead_tmp(addr);
        return 0;
    }

    if ((insn & 0x0f000000) != 0x0e000000)
        return 1;

    switch (((insn >> 12) & 0xf00) | ((insn >> 4) & 0xff)) {
    case 0x000:						/* WOR */
        wrd = (insn >> 12) & 0xf;
        rd0 = (insn >> 0) & 0xf;
        rd1 = (insn >> 16) & 0xf;
        gen_op_iwmmxt_movq_M0_wRn(rd0);
        gen_op_iwmmxt_orq_M0_wRn(rd1);
        gen_op_iwmmxt_setpsr_nz();
        gen_op_iwmmxt_movq_wRn_M0(wrd);
        gen_op_iwmmxt_set_mup();
        gen_op_iwmmxt_set_cup();
        break;
    case 0x011:						/* TMCR */
        if (insn & 0xf)
            return 1;
        rd = (insn >> 12) & 0xf;
        wrd = (insn >> 16) & 0xf;
        switch (wrd) {
        case ARM_IWMMXT_wCID:
        case ARM_IWMMXT_wCASF:
            break;
        case ARM_IWMMXT_wCon:
            gen_op_iwmmxt_set_cup();
            /* Fall through.  */
        case ARM_IWMMXT_wCSSF:
            tmp = iwmmxt_load_creg(wrd);
            tmp2 = load_reg(s, rd);
            tcg_gen_andc_i32(tmp, tmp, tmp2);
            dead_tmp(tmp2);
            iwmmxt_store_creg(wrd, tmp);
            break;
        case ARM_IWMMXT_wCGR0:
        case ARM_IWMMXT_wCGR1:
        case ARM_IWMMXT_wCGR2:
        case ARM_IWMMXT_wCGR3:
            gen_op_iwmmxt_set_cup();
            tmp = load_reg(s, rd);
            iwmmxt_store_creg(wrd, tmp);