/*
 *  m68k translation
 *
 *  Copyright (c) 2005-2007 CodeSourcery
 *  Written by Paul Brook
 *
 * 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 2.1 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 "qemu/osdep.h"
#include "cpu.h"
#include "disas/disas.h"
#include "exec/exec-all.h"
#include "tcg-op.h"
#include "qemu/log.h"
#include "qemu/qemu-print.h"
#include "exec/cpu_ldst.h"
#include "exec/translator.h"

#include "exec/helper-proto.h"
#include "exec/helper-gen.h"

#include "trace-tcg.h"
#include "exec/log.h"
#include "fpu/softfloat.h"


//#define DEBUG_DISPATCH 1

#define DEFO32(name, offset) static TCGv QREG_##name;
#define DEFO64(name, offset) static TCGv_i64 QREG_##name;
#include "qregs.def"
#undef DEFO32
#undef DEFO64

static TCGv_i32 cpu_halted;
static TCGv_i32 cpu_exception_index;

static char cpu_reg_names[2 * 8 * 3 + 5 * 4];
static TCGv cpu_dregs[8];
static TCGv cpu_aregs[8];
static TCGv_i64 cpu_macc[4];

#define REG(insn, pos)  (((insn) >> (pos)) & 7)
#define DREG(insn, pos) cpu_dregs[REG(insn, pos)]
#define AREG(insn, pos) get_areg(s, REG(insn, pos))
#define MACREG(acc)     cpu_macc[acc]
#define QREG_SP         get_areg(s, 7)

static TCGv NULL_QREG;
#define IS_NULL_QREG(t) (t == NULL_QREG)
/* Used to distinguish stores from bad addressing modes.  */
static TCGv store_dummy;

#include "exec/gen-icount.h"

void m68k_tcg_init(void)
{
    char *p;
    int i;

#define DEFO32(name, offset) \
    QREG_##name = tcg_global_mem_new_i32(cpu_env, \
        offsetof(CPUM68KState, offset), #name);
#define DEFO64(name, offset) \
    QREG_##name = tcg_global_mem_new_i64(cpu_env, \
        offsetof(CPUM68KState, offset), #name);
#include "qregs.def"
#undef DEFO32
#undef DEFO64

    cpu_halted = tcg_global_mem_new_i32(cpu_env,
                                        -offsetof(M68kCPU, env) +
                                        offsetof(CPUState, halted), "HALTED");
    cpu_exception_index = tcg_global_mem_new_i32(cpu_env,
                                                 -offsetof(M68kCPU, env) +
                                                 offsetof(CPUState, exception_index),
                                                 "EXCEPTION");

    p = cpu_reg_names;
    for (i = 0; i < 8; i++) {
        sprintf(p, "D%d", i);
        cpu_dregs[i] = tcg_global_mem_new(cpu_env,
                                          offsetof(CPUM68KState, dregs[i]), p);
        p += 3;
        sprintf(p, "A%d", i);
        cpu_aregs[i] = tcg_global_mem_new(cpu_env,
                                          offsetof(CPUM68KState, aregs[i]), p);
        p += 3;
    }
    for (i = 0; i < 4; i++) {
        sprintf(p, "ACC%d", i);
        cpu_macc[i] = tcg_global_mem_new_i64(cpu_env,
                                         offsetof(CPUM68KState, macc[i]), p);
        p += 5;
    }

    NULL_QREG = tcg_global_mem_new(cpu_env, -4, "NULL");
    store_dummy = tcg_global_mem_new(cpu_env, -8, "NULL");
}

/* internal defines */
typedef struct DisasContext {
    DisasContextBase base;
    CPUM68KState *env;
    target_ulong pc;
    CCOp cc_op; /* Current CC operation */
    int cc_op_synced;
    TCGv_i64 mactmp;
    int done_mac;
    int writeback_mask;
    TCGv writeback[8];
#define MAX_TO_RELEASE 8
    int release_count;
    TCGv release[MAX_TO_RELEASE];
} DisasContext;

static void init_release_array(DisasContext *s)
{
#ifdef CONFIG_DEBUG_TCG
    memset(s->release, 0, sizeof(s->release));
#endif
    s->release_count = 0;
}

static void do_release(DisasContext *s)
{
    int i;
    for (i = 0; i < s->release_count; i++) {
        tcg_temp_free(s->release[i]);
    }
    init_release_array(s);
}

static TCGv mark_to_release(DisasContext *s, TCGv tmp)
{
    g_assert(s->release_count < MAX_TO_RELEASE);
    return s->release[s->release_count++] = tmp;
}

static TCGv get_areg(DisasContext *s, unsigned regno)
{
    if (s->writeback_mask & (1 << regno)) {
        return s->writeback[regno];
    } else {
        return cpu_aregs[regno];
    }
}

static void delay_set_areg(DisasContext *s, unsigned regno,
                           TCGv val, bool give_temp)
{
    if (s->writeback_mask & (1 << regno)) {
        if (give_temp) {
            tcg_temp_free(s->writeback[regno]);
            s->writeback[regno] = val;
        } else {
            tcg_gen_mov_i32(s->writeback[regno], val);
        }
    } else {
        s->writeback_mask |= 1 << regno;
        if (give_temp) {
            s->writeback[regno] = val;
        } else {
            TCGv tmp = tcg_temp_new();
            s->writeback[regno] = tmp;
            tcg_gen_mov_i32(tmp, val);
        }
    }
}

static void do_writebacks(DisasContext *s)
{
    unsigned mask = s->writeback_mask;
    if (mask) {
        s->writeback_mask = 0;
        do {
            unsigned regno = ctz32(mask);
            tcg_gen_mov_i32(cpu_aregs[regno], s->writeback[regno]);
            tcg_temp_free(s->writeback[regno]);
            mask &= mask - 1;
        } while (mask);
    }
}

/* is_jmp field values */
#define DISAS_JUMP      DISAS_TARGET_0 /* only pc was modified dynamically */
#define DISAS_EXIT      DISAS_TARGET_1 /* cpu state was modified dynamically */

#if defined(CONFIG_USER_ONLY)
#define IS_USER(s) 1
#else
#define IS_USER(s)   (!(s->base.tb->flags & TB_FLAGS_MSR_S))
#define SFC_INDEX(s) ((s->base.tb->flags & TB_FLAGS_SFC_S) ? \
                      MMU_KERNEL_IDX : MMU_USER_IDX)
#define DFC_INDEX(s) ((s->base.tb->flags & TB_FLAGS_DFC_S) ? \
                      MMU_KERNEL_IDX : MMU_USER_IDX)
#endif

typedef void (*disas_proc)(CPUM68KState *env, DisasContext *s, uint16_t insn);

#ifdef DEBUG_DISPATCH
#define DISAS_INSN(name)                                                \
    static void real_disas_##name(CPUM68KState *env, DisasContext *s,   \
                                  uint16_t insn);                       \
    static void disas_##name(CPUM68KState *env, DisasContext *s,        \
                             uint16_t insn)                             \
    {                                                                   \
        qemu_log("Dispatch " #name "\n");                               \
        real_disas_##name(env, s, insn);                                \
    }                                                                   \
    static void real_disas_##name(CPUM68KState *env, DisasContext *s,   \
                                  uint16_t insn)
#else
#define DISAS_INSN(name)                                                \
    static void disas_##name(CPUM68KState *env, DisasContext *s,        \
                             uint16_t insn)
#endif

static const uint8_t cc_op_live[CC_OP_NB] = {
    [CC_OP_DYNAMIC] = CCF_C | CCF_V | CCF_Z | CCF_N | CCF_X,
    [CC_OP_FLAGS] = CCF_C | CCF_V | CCF_Z | CCF_N | CCF_X,
    [CC_OP_ADDB ... CC_OP_ADDL] = CCF_X | CCF_N | CCF_V,
    [CC_OP_SUBB ... CC_OP_SUBL] = CCF_X | CCF_N | CCF_V,
    [CC_OP_CMPB ... CC_OP_CMPL] = CCF_X | CCF_N | CCF_V,
    [CC_OP_LOGIC] = CCF_X | CCF_N
};

static void set_cc_op(DisasContext *s, CCOp op)
{
    CCOp old_op = s->cc_op;
    int dead;

    if (old_op == op) {
        return;
    }
    s->cc_op = op;
    s->cc_op_synced = 0;

    /*
     * Discard CC computation that will no longer be used.
     * Note that X and N are never dead.
     */
    dead = cc_op_live[old_op] & ~cc_op_live[op];
    if (dead & CCF_C) {
        tcg_gen_discard_i32(QREG_CC_C);
    }
    if (dead & CCF_Z) {
        tcg_gen_discard_i32(QREG_CC_Z);
    }
    if (dead & CCF_V) {
        tcg_gen_discard_i32(QREG_CC_V);
    }
}

/* Update the CPU env CC_OP state.  */
static void update_cc_op(DisasContext *s)
{
    if (!s->cc_op_synced) {
        s->cc_op_synced = 1;
        tcg_gen_movi_i32(QREG_CC_OP, s->cc_op);
    }
}

/* Generate a jump to an immediate address.  */
static void gen_jmp_im(DisasContext *s, uint32_t dest)
{
    update_cc_op(s);
    tcg_gen_movi_i32(QREG_PC, dest);
    s->base.is_jmp = DISAS_JUMP;
}

/* Generate a jump to the address in qreg DEST.  */
static void gen_jmp(DisasContext *s, TCGv dest)
{
    update_cc_op(s);
    tcg_gen_mov_i32(QREG_PC, dest);
    s->base.is_jmp = DISAS_JUMP;
}

static void gen_exception(DisasContext *s, uint32_t dest, int nr)
{
    TCGv_i32 tmp;

    update_cc_op(s);
    tcg_gen_movi_i32(QREG_PC, dest);

    tmp = tcg_const_i32(nr);
    gen_helper_raise_exception(cpu_env, tmp);
    tcg_temp_free_i32(tmp);

    s->base.is_jmp = DISAS_NORETURN;
}

static inline void gen_addr_fault(DisasContext *s)
{
    gen_exception(s, s->base.pc_next, EXCP_ADDRESS);
}

/*
 * Generate a load from the specified address.  Narrow values are
 *  sign extended to full register width.
 */
static inline TCGv gen_load(DisasContext *s, int opsize, TCGv addr,
                            int sign, int index)
{
    TCGv tmp;
    tmp = tcg_temp_new_i32();
    switch(opsize) {
    case OS_BYTE:
        if (sign)
            tcg_gen_qemu_ld8s(tmp, addr, index);
        else
            tcg_gen_qemu_ld8u(tmp, addr, index);
        break;
    case OS_WORD:
        if (sign)
            tcg_gen_qemu_ld16s(tmp, addr, index);
        else
            tcg_gen_qemu_ld16u(tmp, addr, index);
        break;
    case OS_LONG:
        tcg_gen_qemu_ld32u(tmp, addr, index);
        break;
    default:
        g_assert_not_reached();
    }
    return tmp;
}

/* Generate a store.  */
static inline void gen_store(DisasContext *s, int opsize, TCGv addr, TCGv val,
                             int index)
{
    switch(opsize) {
    case OS_BYTE:
        tcg_gen_qemu_st8(val, addr, index);
        break;
    case OS_WORD:
        tcg_gen_qemu_st16(val, addr, index);
        break;
    case OS_LONG:
        tcg_gen_qemu_st32(val, addr, index);
        break;
    default:
        g_assert_not_reached();
    }
}

typedef enum {
    EA_STORE,
    EA_LOADU,
    EA_LOADS
} ea_what;

/*
 * Generate an unsigned load if VAL is 0 a signed load if val is -1,
 * otherwise generate a store.
 */
static TCGv gen_ldst(DisasContext *s, int opsize, TCGv addr, TCGv val,
                     ea_what what, int index)
{
    if (what == EA_STORE) {
        gen_store(s, opsize, addr, val, index);
        return store_dummy;
    } else {
        return mark_to_release(s, gen_load(s, opsize, addr,
                                           what == EA_LOADS, index));
    }
}

/* Read a 16-bit immediate constant */
static inline uint16_t read_im16(CPUM68KState *env, DisasContext *s)
{
    uint16_t im;
    im = cpu_lduw_code(env, s->pc);
    s->pc += 2;
    return im;
}

/* Read an 8-bit immediate constant */
static inline uint8_t read_im8(CPUM68KState *env, DisasContext *s)
{
    return read_im16(env, s);
}

/* Read a 32-bit immediate constant.  */
static inline uint32_t read_im32(CPUM68KState *env, DisasContext *s)
{
    uint32_t im;
    im = read_im16(env, s) << 16;
    im |= 0xffff & read_im16(env, s);
    return im;
}

/* Read a 64-bit immediate constant.  */
static inline uint64_t read_im64(CPUM68KState *env, DisasContext *s)
{
    uint64_t im;
    im = (uint64_t)read_im32(env, s) << 32;
    im |= (uint64_t)read_im32(env, s);
    return im;
}

/* Calculate and address index.  */
static TCGv gen_addr_index(DisasContext *s, uint16_t ext, TCGv tmp)
{
    TCGv add;
    int scale;

    add = (ext & 0x8000) ? AREG(ext, 12) : DREG(ext, 12);
    if ((ext & 0x800) == 0) {
        tcg_gen_ext16s_i32(tmp, add);
        add = tmp;
    }
    scale = (ext >> 9) & 3;
    if (scale != 0) {
        tcg_gen_shli_i32(tmp, add, scale);
        add = tmp;
    }
    return add;
}

/*
 * Handle a base + index + displacement effective addresss.
 * A NULL_QREG base means pc-relative.
 */
static TCGv gen_lea_indexed(CPUM68KState *env, DisasContext *s, TCGv base)
{
    uint32_t offset;
    uint16_t ext;
    TCGv add;
    TCGv tmp;
    uint32_t bd, od;

    offset = s->pc;
    ext = read_im16(env, s);

    if ((ext & 0x800) == 0 && !m68k_feature(s->env, M68K_FEATURE_WORD_INDEX))
        return NULL_QREG;

    if (m68k_feature(s->env, M68K_FEATURE_M68000) &&
        !m68k_feature(s->env, M68K_FEATURE_SCALED_INDEX)) {
        ext &= ~(3 << 9);
    }

    if (ext & 0x100) {
        /* full extension word format */
        if (!m68k_feature(s->env, M68K_FEATURE_EXT_FULL))
            return NULL_QREG;

        if ((ext & 0x30) > 0x10) {
            /* base displacement */
            if ((ext & 0x30) == 0x20) {
                bd = (int16_t)read_im16(env, s);
            } else {
                bd = read_im32(env, s);
            }
        } else {
            bd = 0;
        }
        tmp = mark_to_release(s, tcg_temp_new());
        if ((ext & 0x44) == 0) {
            /* pre-index */
            add = gen_addr_index(s, ext, tmp);
        } else {
            add = NULL_QREG;
        }
        if ((ext & 0x80) == 0) {
            /* base not suppressed */
            if (IS_NULL_QREG(base)) {
                base = mark_to_release(s, tcg_const_i32(offset + bd));
                bd = 0;
            }
            if (!IS_NULL_QREG(add)) {
                tcg_gen_add_i32(tmp, add, base);
                add = tmp;
            } else {
                add = base;
            }
        }
        if (!IS_NULL_QREG(add)) {
            if (bd != 0) {
                tcg_gen_addi_i32(tmp, add, bd);
                add = tmp;
            }
        } else {
            add = mark_to_release(s, tcg_const_i32(bd));
        }
        if ((ext & 3) != 0) {
            /* memory indirect */
            base = mark_to_release(s, gen_load(s, OS_LONG, add, 0, IS_USER(s)));
            if ((ext & 0x44) == 4) {
                add = gen_addr_index(s, ext, tmp);
                tcg_gen_add_i32(tmp, add, base);
                add = tmp;
            } else {
                add = base;
            }
            if ((ext & 3) > 1) {
                /* outer displacement */
                if ((ext & 3) == 2) {
                    od = (int16_t)read_im16(env, s);
                } else {
                    od = read_im32(env, s);
                }
            } else {
                od = 0;
            }
            if (od != 0) {
                tcg_gen_addi_i32(tmp, add, od);
                add = tmp;
            }
        }
    } else {
        /* brief extension word format */
        tmp = mark_to_release(s, tcg_temp_new());
        add = gen_addr_index(s, ext, tmp);
        if (!IS_NULL_QREG(base)) {
            tcg_gen_add_i32(tmp, add, base);
            if ((int8_t)ext)
                tcg_gen_addi_i32(tmp, tmp, (int8_t)ext);
        } else {
            tcg_gen_addi_i32(tmp, add, offset + (int8_t)ext);
        }
        add = tmp;
    }
    return add;
}

/* Sign or zero extend a value.  */

static inline void gen_ext(TCGv res, TCGv val, int opsize, int sign)
{
    switch (opsize) {
    case OS_BYTE:
        if (sign) {
            tcg_gen_ext8s_i32(res, val);
        } else {
            tcg_gen_ext8u_i32(res, val);
        }
        break;
    case OS_WORD:
        if (sign) {
            tcg_gen_ext16s_i32(res, val);
        } else {
            tcg_gen_ext16u_i32(res, val);
        }
        break;
    case OS_LONG:
        tcg_gen_mov_i32(res, val);
        break;
    default:
        g_assert_not_reached();
    }
}

/* Evaluate all the CC flags.  */

static void gen_flush_flags(DisasContext *s)
{
    TCGv t0, t1;

    switch (s->cc_op) {
    case CC_OP_FLAGS:
        return;

    case CC_OP_ADDB:
    case CC_OP_ADDW:
    case CC_OP_ADDL:
        tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);
        tcg_gen_mov_i32(QREG_CC_Z, QREG_CC_N);
        /* Compute signed overflow for addition.  */
        t0 = tcg_temp_new();
        t1 = tcg_temp_new();
        tcg_gen_sub_i32(t0, QREG_CC_N, QREG_CC_V);
        gen_ext(t0, t0, s->cc_op - CC_OP_ADDB, 1);
        tcg_gen_xor_i32(t1, QREG_CC_N, QREG_CC_V);
        tcg_gen_xor_i32(QREG_CC_V, QREG_CC_V, t0);
        tcg_temp_free(t0);
        tcg_gen_andc_i32(QREG_CC_V, t1, QREG_CC_V);
        tcg_temp_free(t1);
        break;

    case CC_OP_SUBB:
    case CC_OP_SUBW:
    case CC_OP_SUBL:
        tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);
        tcg_gen_mov_i32(QREG_CC_Z, QREG_CC_N);
        /* Compute signed overflow for subtraction.  */
        t0 = tcg_temp_new();
        t1 = tcg_temp_new();
        tcg_gen_add_i32(t0, QREG_CC_N, QREG_CC_V);
        gen_ext(t0, t0, s->cc_op - CC_OP_SUBB, 1);
        tcg_gen_xor_i32(t1, QREG_CC_N, t0);
        tcg_gen_xor_i32(QREG_CC_V, QREG_CC_V, t0);
        tcg_temp_free(t0);
        tcg_gen_and_i32(QREG_CC_V, QREG_CC_V, t1);
        tcg_temp_free(t1);
        break;

    case CC_OP_CMPB:
    case CC_OP_CMPW:
    case CC_OP_CMPL:
        tcg_gen_setcond_i32(TCG_COND_LTU, QREG_CC_C, QREG_CC_N, QREG_CC_V);
        tcg_gen_sub_i32(QREG_CC_Z, QREG_CC_N, QREG_CC_V);
        gen_ext(QREG_CC_Z, QREG_CC_Z, s->cc_op - CC_OP_CMPB, 1);
        /* Compute signed overflow for subtraction.  */
        t0 = tcg_temp_new();
        tcg_gen_xor_i32(t0, QREG_CC_Z, QREG_CC_N);
        tcg_gen_xor_i32(QREG_CC_V, QREG_CC_V, QREG_CC_N);
        tcg_gen_and_i32(QREG_CC_V, QREG_CC_V, t0);
        tcg_temp_free(t0);
        tcg_gen_mov_i32(QREG_CC_N, QREG_CC_Z);
        break;

    case CC_OP_LOGIC:
        tcg_gen_mov_i32(QREG_CC_Z, QREG_CC_N);
        tcg_gen_movi_i32(QREG_CC_C, 0);
        tcg_gen_movi_i32(QREG_CC_V, 0);
        break;

    case CC_OP_DYNAMIC:
        gen_helper_flush_flags(cpu_env, QREG_CC_OP);
        s->cc_op_synced = 1;
        break;

    default:
        t0 = tcg_const_i32(s->cc_op);
        gen_helper_flush_flags(cpu_env, t0);
        tcg_temp_free(t0);
        s->cc_op_synced = 1;
        break;
    }

    /* Note that flush_flags also assigned to env->cc_op.  */
    s->cc_op = CC_OP_FLAGS;
}

static inline TCGv gen_extend(DisasContext *s, TCGv val, int opsize, int sign)
{
    TCGv tmp;

    if (opsize == OS_LONG) {
        tmp = val;
    } else {
        tmp = mark_to_release(s, tcg_temp_new());
        gen_ext(tmp, val, opsize, sign);
    }

    return tmp;
}

static void gen_logic_cc(DisasContext *s, TCGv val, int opsize)
{
    gen_ext(QREG_CC_N, val, opsize, 1);
    set_cc_op(s, CC_OP_LOGIC);
}

static void gen_update_cc_cmp(DisasContext *s, TCGv dest, TCGv src, int opsize)
{
    tcg_gen_mov_i32(QREG_CC_N, dest);
    tcg_gen_mov_i32(QREG_CC_V, src);
    set_cc_op(s, CC_OP_CMPB + opsize);
}

static void gen_update_cc_add(TCGv dest, TCGv src, int opsize)
{
    gen_ext(QREG_CC_N, dest, opsize, 1);
    tcg_gen_mov_i32(QREG_CC_V, src);
}

static inline int opsize_bytes(int opsize)
{
    switch (opsize) {
    case OS_BYTE: return 1;
    case OS_WORD: return 2;
    case OS_LONG: return 4;
    case OS_SINGLE: return 4;
    case OS_DOUBLE: return 8;
    case OS_EXTENDED: return 12;
    case OS_PACKED: return 12;
    default:
        g_assert_not_reached();
    }
}

static inline int insn_opsize(int insn)
{
    switch ((insn >> 6) & 3) {
    case 0: return OS_BYTE;
    case 1: return OS_WORD;
    case 2: return OS_LONG;
    default:
        g_assert_not_reached();
    }
}

static inline int ext_opsize(int ext, int pos)
{
    switch ((ext >> pos) & 7) {
    case 0: return OS_LONG;
    case 1: return OS_SINGLE;
    case 2: return OS_EXTENDED;
    case 3: return OS_PACKED;
    case 4: return OS_WORD;
    case 5: return OS_DOUBLE;
    case 6: return OS_BYTE;
    default:
        g_assert_not_reached();
    }
}

/*
 * Assign value to a register.  If the width is less than the register width
 * only the low part of the register is set.
 */
static void gen_partset_reg(int opsize, TCGv reg, TCGv val)
{
    TCGv tmp;
    switch (opsize) {
    case OS_BYTE:
        tcg_gen_andi_i32(reg, reg, 0xffffff00);
        tmp = tcg_temp_new();
        tcg_gen_ext8u_i32(tmp, val);
        tcg_gen_or_i32(reg, reg, tmp);
        tcg_temp_free(tmp);
        break;
    case OS_WORD:
        tcg_gen_andi_i32(reg, reg, 0xffff0000);
        tmp = tcg_temp_new();
        tcg_gen_ext16u_i32(tmp, val);
        tcg_gen_or_i32(reg, reg, tmp);
        tcg_temp_free(tmp);
        break;
    case OS_LONG:
    case OS_SINGLE:
        tcg_gen_mov_i32(reg, val);
        break;
    default:
        g_assert_not_reached();
    }
}

/*
 * Generate code for an "effective address".  Does not adjust the base
 * register for autoincrement addressing modes.
 */
static TCGv gen_lea_mode(CPUM68KState *env, DisasContext *s,
                         int mode, int reg0, int opsize)
{
    TCGv reg;
    TCGv tmp;
    uint16_t ext;
    uint32_t offset;

    switch (mode) {
    case 0: /* Data register direct.  */
    case 1: /* Address register direct.  */
        return NULL_QREG;
    case 3: /* Indirect postincrement.  */
        if (opsize == OS_UNSIZED) {
            return NULL_QREG;
        }
        /* fallthru */
    case 2: /* Indirect register */
        return get_areg(s, reg0);
    case 4: /* Indirect predecrememnt.  */
        if (opsize == OS_UNSIZED) {
            return NULL_QREG;
        }
        reg = get_areg(s, reg0);
        tmp = mark_to_release(s, tcg_temp_new());
        if (reg0 == 7 && opsize == OS_BYTE &&
            m68k_feature(s->env, M68K_FEATURE_M68000)) {
            tcg_gen_subi_i32(tmp, reg, 2);
        } else {
            tcg_gen_subi_i32(tmp, reg, opsize_bytes(opsize));
        }
        return tmp;
    case 5: /* Indirect displacement.  */
        reg = get_areg(s, reg0);
        tmp = mark_to_release(s, tcg_temp_new());
        ext = read_im16(env, s);
        tcg_gen_addi_i32(tmp, reg, (int16_t)ext);
        return tmp;
    case 6: /* Indirect index + displacement.  */
        reg = get_areg(s, reg0);
        return gen_lea_indexed(env, s, reg);
    case 7: /* Other */
        switch (reg0) {
        case 0: /* Absolute short.  */
            offset = (int16_t)read_im16(env, s);
            return mark_to_release(s, tcg_const_i32(offset));
        case 1: /* Absolute long.  */
            offset = read_im32(env, s);
            return mark_to_release(s, tcg_const_i32(offset));
        case 2: /* pc displacement  */
            offset = s->pc;
            offset += (int16_t)read_im16(env, s);
            return mark_to_release(s, tcg_const_i32(offset));
        case 3: /* pc index+displacement.  */
            return gen_lea_indexed(env, s, NULL_QREG);
        case 4: /* Immediate.  */
        default:
            return NULL_QREG;
        }
    }
    /* Should never happen.  */
    return NULL_QREG;
}

static TCGv gen_lea(CPUM68KState *env, DisasContext *s, uint16_t insn,
                    int opsize)
{
    int mode = extract32(insn, 3, 3);
    int reg0 = REG(insn, 0);
    return gen_lea_mode(env, s, mode, reg0, opsize);
}

/*
 * Generate code to load/store a value from/into an EA.  If WHAT > 0 this is
 * a write otherwise it is a read (0 == sign extend, -1 == zero extend).
 * ADDRP is non-null for readwrite operands.
 */
static TCGv gen_ea_mode(CPUM68KState *env, DisasContext *s, int mode, int reg0,
                        int opsize, TCGv val, TCGv *addrp, ea_what what,
                        int index)
{
    TCGv reg, tmp, result;
    int32_t offset;

    switch (mode) {
    case 0: /* Data register direct.  */
        reg = cpu_dregs[reg0];
        if (what == EA_STORE) {
            gen_partset_reg(opsize, reg, val);
            return store_dummy;
        } else {
            return gen_extend(s, reg, opsize, what == EA_LOADS);
        }
    case 1: /* Address register direct.  */
        reg = get_areg(s, reg0);
        if (what == EA_STORE) {
            tcg_gen_mov_i32(reg, val);
            return store_dummy;
        } else {
            return gen_extend(s, reg, opsize, what == EA_LOADS);
        }
    case 2: /* Indirect register */
        reg = get_areg(s, reg0);
        return gen_ldst(s, opsize, reg, val, what, index);
    case 3: /* Indirect postincrement.  */
        reg = get_areg(s, reg0);
        result = gen_ldst(s, opsize, reg, val, what, index);
        if (what == EA_STORE || !addrp) {
            TCGv tmp = tcg_temp_new();
            if (reg0 == 7 && opsize == OS_BYTE &&
                m68k_feature(s->env, M68K_FEATURE_M68000)) {
                tcg_gen_addi_i32(tmp, reg, 2);
            } else {
                tcg_gen_addi_i32(tmp, reg, opsize_bytes(opsize));
            }
            delay_set_areg(s, reg0, tmp, true);
        }
        return result;
    case 4: /* Indirect predecrememnt.  */
        if (addrp && what == EA_STORE) {
            tmp = *addrp;
        } else {
            tmp = gen_lea_mode(env, s, mode, reg0, opsize);
            if (IS_NULL_QREG(tmp)) {
                return tmp;
            }
            if (addrp) {
                *addrp = tmp;
            }
        }
        result = gen_ldst(s, opsize, tmp, val, what, index);
        if (what == EA_STORE || !addrp) {
            delay_set_areg(s, reg0, tmp, false);
        }
        return result;
    case 5: /* Indirect displacement.  */
    case 6: /* Indirect index + displacement.  */
    do_indirect:
        if (addrp && what == EA_STORE) {
            tmp = *addrp;
        } else {
            tmp = gen_lea_mode(env, s, mode, reg0, opsize);
            if (IS_NULL_QREG(tmp)) {
                return tmp;
            }
            if (addrp) {
                *addrp = tmp;
            }
        }
        return gen_ldst(s, opsize, tmp, val, what, index);
    case 7: /* Other */
        switch (reg0) {
        case 0: /* Absolute short.  */
        case 1: /* Absolute long.  */
        case 2: /* pc displacement  */
        case 3: /* pc index+displacement.  */
            goto do_indirect;
        case 4: /* Immediate.  */
            /* Sign extend values for consistency.  */
            switch (opsize) {
            case OS_BYTE:
                if (what == EA_LOADS) {
                    offset = (int8_t)read_im8(env, s);
                } else {
                    offset = read_im8(env, s);
                }
                break;
            case OS_WORD:
                if (what == EA_LOADS) {
                    offset = (int16_t)read_im16(env, s);
                } else {
                    offset = read_im16(env, s);
                }
                break;
            case OS_LONG:
                offset = read_im32(env, s);
                break;
            default:
                g_assert_not_reached();
            }
            return mark_to_release(s, tcg_const_i32(offset));
        default:
            return NULL_QREG;
        }
    }
    /* Should never happen.  */
    return NULL_QREG;
}

static TCGv gen_ea(CPUM68KState *env, DisasContext *s, uint16_t insn,
                   int opsize, TCGv val, TCGv *addrp, ea_what what, int index)
{
    int mode = extract32(insn, 3, 3);
    int reg0 = REG(insn, 0);
    return gen_ea_mode(env, s, mode, reg0, opsize, val, addrp, what, index);
}

static TCGv_ptr gen_fp_ptr(int freg)
{
    TCGv_ptr fp = tcg_temp_new_ptr();
    tcg_gen_addi_ptr(fp, cpu_env, offsetof(CPUM68KState, fregs[freg]));
    return fp;
}

static TCGv_ptr gen_fp_result_ptr(void)
{
    TCGv_ptr fp = tcg_temp_new_ptr();
    tcg_gen_addi_ptr(fp, cpu_env, offsetof(CPUM68KState, fp_result));
    return fp;
}

static void gen_fp_move(TCGv_ptr dest, TCGv_ptr src)
{
    TCGv t32;
    TCGv_i64 t64;

    t32 = tcg_temp_new();
    tcg_gen_ld16u_i32(t32, src, offsetof(FPReg, l.upper));
    tcg_gen_st16_i32(t32, dest, offsetof(FPReg, l.upper));
    tcg_temp_free(t32);

    t64 = tcg_temp_new_i64();
    tcg_gen_ld_i64(t64, src, offsetof(FPReg, l.lower));
    tcg_gen_st_i64(t64, dest, offsetof(FPReg, l.lower));
    tcg_temp_free_i64(t64);
}

static void gen_load_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
                        int index)
{
    TCGv tmp;
    TCGv_i64 t64;

    t64 = tcg_temp_new_i64();
    tmp = tcg_temp_new();
    switch (opsize) {
    case OS_BYTE:
        tcg_gen_qemu_ld8s(tmp, addr, index);
        gen_helper_exts32(cpu_env, fp, tmp);
        break;
    case OS_WORD:

        tcg_gen_qemu_ld16s(tmp, addr, index);
        gen_helper_exts32(cpu_env, fp, tmp);
        break;
    case OS_LONG:
        tcg_gen_qemu_ld32u(tmp, addr, index);
        gen_helper_exts32(cpu_env, fp, tmp);
        break;
    case OS_SINGLE:
        tcg_gen_qemu_ld32u(tmp, addr, index);
        gen_helper_extf32(cpu_env, fp, tmp);
        break;
    case OS_DOUBLE:
        tcg_gen_qemu_ld64(t64, addr, index);
        gen_helper_extf64(cpu_env, fp, t64);
        break;
    case OS_EXTENDED:
        if (m68k_feature(s->env, M68K_FEATURE_CF_FPU)) {
            gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
            break;
        }
        tcg_gen_qemu_ld32u(tmp, addr, index);
        tcg_gen_shri_i32(tmp, tmp, 16);
        tcg_gen_st16_i32(tmp, fp, offsetof(FPReg, l.upper));
        tcg_gen_addi_i32(tmp, addr, 4);
        tcg_gen_qemu_ld64(t64, tmp, index);
        tcg_gen_st_i64(t64, fp, offsetof(FPReg, l.lower));
        break;
    case OS_PACKED:
        /*
         * unimplemented data type on 68040/ColdFire
         * FIXME if needed for another FPU
         */
        gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
        break;
    default:
        g_assert_not_reached();
    }
    tcg_temp_free(tmp);
    tcg_temp_free_i64(t64);
}

static void gen_store_fp(DisasContext *s, int opsize, TCGv addr, TCGv_ptr fp,
                         int index)
{
    TCGv tmp;
    TCGv_i64 t64;

    t64 = tcg_temp_new_i64();
    tmp = tcg_temp_new();
    switch (opsize) {
    case OS_BYTE:
        gen_helper_reds32(tmp, cpu_env, fp);
        tcg_gen_qemu_st8(tmp, addr, index);
        break;
    case OS_WORD:
        gen_helper_reds32(tmp, cpu_env, fp);
        tcg_gen_qemu_st16(tmp, addr, index);
        break;
    case OS_LONG:
        gen_helper_reds32(tmp, cpu_env, fp);
        tcg_gen_qemu_st32(tmp, addr, index);
        break;
    case OS_SINGLE:
        gen_helper_redf32(tmp, cpu_env, fp);
        tcg_gen_qemu_st32(tmp, addr, index);
        break;
    case OS_DOUBLE:
        gen_helper_redf64(t64, cpu_env, fp);
        tcg_gen_qemu_st64(t64, addr, index);
        break;
    case OS_EXTENDED:
        if (m68k_feature(s->env, M68K_FEATURE_CF_FPU)) {
            gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
            break;
        }
        tcg_gen_ld16u_i32(tmp, fp, offsetof(FPReg, l.upper));
        tcg_gen_shli_i32(tmp, tmp, 16);
        tcg_gen_qemu_st32(tmp, addr, index);
        tcg_gen_addi_i32(tmp, addr, 4);
        tcg_gen_ld_i64(t64, fp, offsetof(FPReg, l.lower));
        tcg_gen_qemu_st64(t64, tmp, index);
        break;
    case OS_PACKED:
        /*
         * unimplemented data type on 68040/ColdFire
         * FIXME if needed for another FPU
         */
        gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
        break;
    default:
        g_assert_not_reached();
    }
    tcg_temp_free(tmp);
    tcg_temp_free_i64(t64);
}

static void gen_ldst_fp(DisasContext *s, int opsize, TCGv addr,
                        TCGv_ptr fp, ea_what what, int index)
{
    if (what == EA_STORE) {
        gen_store_fp(s, opsize, addr, fp, index);
    } else {
        gen_load_fp(s, opsize, addr, fp, index);
    }
}

static int gen_ea_mode_fp(CPUM68KState *env, DisasContext *s, int mode,
                          int reg0, int opsize, TCGv_ptr fp, ea_what what,
                          int index)
{
    TCGv reg, addr, tmp;
    TCGv_i64 t64;

    switch (mode) {
    case 0: /* Data register direct.  */
        reg = cpu_dregs[reg0];
        if (what == EA_STORE) {
            switch (opsize) {
            case OS_BYTE:
            case OS_WORD:
            case OS_LONG:
                gen_helper_reds32(reg, cpu_env, fp);
                break;
            case OS_SINGLE:
                gen_helper_redf32(reg, cpu_env, fp);
                break;
            default:
                g_assert_not_reached();
            }
        } else {
            tmp = tcg_temp_new();
            switch (opsize) {
            case OS_BYTE:
                tcg_gen_ext8s_i32(tmp, reg);
                gen_helper_exts32(cpu_env, fp, tmp);
                break;
            case OS_WORD:
                tcg_gen_ext16s_i32(tmp, reg);
                gen_helper_exts32(cpu_env, fp, tmp);
                break;
            case OS_LONG:
                gen_helper_exts32(cpu_env, fp, reg);
                break;
            case OS_SINGLE:
                gen_helper_extf32(cpu_env, fp, reg);
                break;
            default:
                g_assert_not_reached();
            }
            tcg_temp_free(tmp);
        }
        return 0;
    case 1: /* Address register direct.  */
        return -1;
    case 2: /* Indirect register */
        addr = get_areg(s, reg0);
        gen_ldst_fp(s, opsize, addr, fp, what, index);
        return 0;
    case 3: /* Indirect postincrement.  */
        addr = cpu_aregs[reg0];
        gen_ldst_fp(s, opsize, addr, fp, what, index);
        tcg_gen_addi_i32(addr, addr, opsize_bytes(opsize));
        return 0;
    case 4: /* Indirect predecrememnt.  */
        addr = gen_lea_mode(env, s, mode, reg0, opsize);
        if (IS_NULL_QREG(addr)) {
            return -1;
        }
        gen_ldst_fp(s, opsize, addr, fp, what, index);
        tcg_gen_mov_i32(cpu_aregs[reg0], addr);
        return 0;
    case 5: /* Indirect displacement.  */
    case 6: /* Indirect index + displacement.  */
    do_indirect:
        addr = gen_lea_mode(env, s, mode, reg0, opsize);
        if (IS_NULL_QREG(addr)) {
            return -1;
        }
        gen_ldst_fp(s, opsize, addr, fp, what, index);
        return 0;
    case 7: /* Other */
        switch (reg0) {
        case 0: /* Absolute short.  */
        case 1: /* Absolute long.  */
        case 2: /* pc displacement  */
        case 3: /* pc index+displacement.  */
            goto do_indirect;
        case 4: /* Immediate.  */
            if (what == EA_STORE) {
                return -1;
            }
            switch (opsize) {
            case OS_BYTE:
                tmp = tcg_const_i32((int8_t)read_im8(env, s));
                gen_helper_exts32(cpu_env, fp, tmp);
                tcg_temp_free(tmp);
                break;
            case OS_WORD:
                tmp = tcg_const_i32((int16_t)read_im16(env, s));
                gen_helper_exts32(cpu_env, fp, tmp);
                tcg_temp_free(tmp);
                break;
            case OS_LONG:
                tmp = tcg_const_i32(read_im32(env, s));
                gen_helper_exts32(cpu_env, fp, tmp);
                tcg_temp_free(tmp);
                break;
            case OS_SINGLE:
                tmp = tcg_const_i32(read_im32(env, s));
                gen_helper_extf32(cpu_env, fp, tmp);
                tcg_temp_free(tmp);
                break;
            case OS_DOUBLE:
                t64 = tcg_const_i64(read_im64(env, s));
                gen_helper_extf64(cpu_env, fp, t64);
                tcg_temp_free_i64(t64);
                break;
            case OS_EXTENDED:
                if (m68k_feature(s->env, M68K_FEATURE_CF_FPU)) {
                    gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
                    break;
                }
                tmp = tcg_const_i32(read_im32(env, s) >> 16);
                tcg_gen_st16_i32(tmp, fp, offsetof(FPReg, l.upper));
                tcg_temp_free(tmp);
                t64 = tcg_const_i64(read_im64(env, s));
                tcg_gen_st_i64(t64, fp, offsetof(FPReg, l.lower));
                tcg_temp_free_i64(t64);
                break;
            case OS_PACKED:
                /*
                 * unimplemented data type on 68040/ColdFire
                 * FIXME if needed for another FPU
                 */
                gen_exception(s, s->base.pc_next, EXCP_FP_UNIMP);
                break;
            default:
                g_assert_not_reached();
            }
            return 0;
        default:
            return -1;
        }
    }
    return -1;
}

static int gen_ea_fp(CPUM68KState *env, DisasContext *s, uint16_t insn,
                       int opsize, TCGv_ptr fp, ea_what what, int index)
{
    int mode = extract32(insn, 3, 3);
    int reg0 = REG(insn, 0);
    return gen_ea_mode_fp(env, s, mode, reg0, opsize, fp, what, index);
}

typedef struct {
    TCGCond tcond;
    bool g1;
    bool g2;
    TCGv v1;
    TCGv v2;
} DisasCompare;

static void gen_cc_cond(DisasCompare *c, DisasContext *s, int cond)
{
    TCGv tmp, tmp2;
    TCGCond tcond;
    CCOp op = s->cc_op;

    /* The CC_OP_CMP form can handle most normal comparisons directly.  */
    if (op == CC_OP_CMPB || op == CC_OP_CMPW || op == CC_OP_CMPL) {
        c->g1 = c->g2 = 1;
        c->v1 = QREG_CC_N;
        c->v2 = QREG_CC_V;
        switch (cond) {
        case 2: /* HI */
        case 3: /* LS */
            tcond = TCG_COND_LEU;
            goto done;
        case 4: /* CC */
        case 5: /* CS */
            tcond = TCG_COND_LTU;
            goto done;
        case 6: /* NE */
        case 7: /* EQ */
            tcond = TCG_COND_EQ;
            goto done;
        case 10: /* PL */
        case 11: /* MI */
            c->g1 = c->g2 = 0;
            c->v2 = tcg_const_i32(0);
            c->v1 = tmp = tcg_temp_new();
            tcg_gen_sub_i32(tmp, QREG_CC_N, QREG_CC_V);
            gen_ext(tmp, tmp, op - CC_OP_CMPB, 1);
            /* fallthru */
        case 12: /* GE */
        case 13: /* LT */
            tcond = TCG_COND_LT;
            goto done;
        case 14: /* GT */
        case 15: /* LE */
            tcond = TCG_COND_LE;
            goto done;
        }
    }

    c->g1 = 1;
    c->g2 = 0;
    c->v2 = tcg_const_i32(0);

    switch (cond) {
    case 0: /* T */
    case 1: /* F */
        c->v1 = c->v2;
        tcond = TCG_COND_NEVER;
        goto done;
    case 14: /* GT (!(Z || (N ^ V))) */
    case 15: /* LE (Z || (N ^ V)) */
        /*
         * Logic operations clear V, which simplifies LE to (Z || N),
         * and since Z and N are co-located, this becomes a normal
         * comparison vs N.
         */
        if (op == CC_OP_LOGIC) {
            c->v1 = QREG_CC_N;
            tcond = TCG_COND_LE;
            goto done;
        }
        break;
    case 12: /* GE (!(N ^ V)) */
    case 13: /* LT (N ^ V) */
        /* Logic operations clear V, which simplifies this to N.  */
        if (op != CC_OP_LOGIC) {
            break;
        }
        /* fallthru */
    case 10: /* PL (!N) */
    case 11: /* MI (N) */
        /* Several cases represent N normally.  */
        if (op == CC_OP_ADDB || op == CC_OP_ADDW || op == CC_OP_ADDL ||
            op == CC_OP_SUBB || op == CC_OP_SUBW || op == CC_OP_SUBL ||
            op == CC_OP_LOGIC) {
            c->v1 = QREG_CC_N;
            tcond = TCG_COND_LT;
            goto done;
        }
        break;
    case 6: /* NE (!Z) */
    case 7: /* EQ (Z) */
        /* Some cases fold Z into N.  */
        if (op == CC_OP_ADDB || op == CC_OP_ADDW || op == CC_OP_ADDL ||
            op == CC_OP_SUBB || op == CC_OP_SUBW || op == CC_OP_SUBL ||
            op == CC_OP_LOGIC) {
            tcond = TCG_COND_EQ;
            c->v1 = QREG_CC_N;
            goto done;
        }
        break;
    case 4: /* CC (!C) */
    case 5: /* CS (C) */
        /* Some cases fold C into X.  */
        if (op == CC_OP_ADDB || op == CC_OP_ADDW || op == CC_OP_ADDL ||
            op == CC_OP_SUBB || op == CC_OP_SUBW || op == CC_OP_SUBL) {
            tcond = TCG_COND_NE;
            c->v1 = QREG_CC_X;
            goto done;
        }
        /* fallthru */
    case 8: /* VC (!V) */
    case 9: /* VS (V) */
        /* Logic operations clear V and C.  */
        if (op == CC_OP_LOGIC) {
            tcond = TCG_COND_NEVER;
            c->v1 = c->v2;
            goto done;
        }
        break;
    }

    /* Otherwise, flush flag state to CC_OP_FLAGS.  */
    gen_flush_flags(s);

    switch (cond) {
    case 0: /* T */
    case 1: /* F */
    default:
        /* Invalid, or handled above.  */
        abort();
    case 2: /* HI (!C && !Z) -> !(C || Z)*/
    case 3: /* LS (C || Z) */
        c->v1 = tmp = tcg_temp_new();
        c->g1 = 0;
        tcg_gen_setcond_i32(TCG_COND_EQ, tmp, QREG_CC_Z, c->v2);
        tcg_gen_or_i32(tmp, tmp, QREG_CC_C);
        tcond = TCG_COND_NE;
        break;
    case 4: /* CC (!C) */
    case 5: /* CS (C) */
        c->v1 = QREG_CC_C;
        tcond = TCG_COND_NE;
        break;
    case 6: /* NE (!Z) */
    case 7: /* EQ (Z) */
        c->v1 = QREG_CC_Z;
        tcond = TCG_COND_EQ;
        break;
    case 8: /* VC (!V) */
    case 9: /* VS (V) */
        c->v1 = QREG_CC_V;
        tcond = TCG_COND_LT;
        break;
    case 10: /* PL (!N) */
    case 11: /* MI (N) */
        c->v1 = QREG_CC_N;
        tcond = TCG_COND_LT;
        break;
    case 12: /* GE (!(N ^ V)) */
    case 13: /* LT (N ^ V) */
        c->v1 = tmp = tcg_temp_new();
        c->g1 = 0;
        tcg_gen_xor_i32(tmp, QREG_CC_N, QREG_CC_V);
        tcond = TCG_COND_LT;
        break;
    case 14: /* GT (!(Z || (N ^ V))) */
    case 15: /* LE (Z || (N ^ V)) */
        c->v1 = tmp = tcg_temp_new();
        c->g1 = 0;
        tcg_gen_setcond_i32(TCG_COND_EQ, tmp, QREG_CC_Z, c->v2);
        tcg_gen_neg_i32(tmp, tmp);
        tmp2 = tcg_temp_new();
        tcg_gen_xor_i32(tmp2, QREG_CC_N, QREG_CC_V);
        tcg_gen_or_i32(tmp, tmp, tmp2);
        tcg_temp_free(tmp2);
        tcond = TCG_COND_LT;
        break;
    }

 done:
    if ((cond & 1) == 0) {
        tcond = tcg_invert_cond(tcond);
    }
    c->tcond = tcond;
}

static void free_cond(DisasCompare *c)
{
    if (!c->g1) {
        tcg_temp_free(c->v1);
    }
    if (!c->g2) {
        tcg_temp_free(c->v2);
    }
}

static void gen_jmpcc(DisasContext *s, int cond, TCGLabel *l1)
{
  DisasCompare c;

  gen_cc_cond(&c, s, cond);
  update_cc_op(s);
  tcg_gen_brcond_i32(c.tcond, c.v1, c.v2, l1);
  free_cond(&c);
}

/* Force a TB lookup after an instruction that changes the CPU state.  */
static void gen_exit_tb(DisasContext *s)
{
    update_cc_op(s);
    tcg_gen_movi_i32(QREG_PC, s->pc);
    s->base.is_jmp = DISAS_EXIT;
}

#define SRC_EA(env, result, opsize, op_sign, addrp) do {                \
        result = gen_ea(env, s, insn, opsize, NULL_QREG, addrp,         \
                        op_sign ? EA_LOADS : EA_LOADU, IS_USER(s));     \
        if (IS_NULL_QREG(result)) {                                     \
            gen_addr_fault(s);                                          \
            return;                                                     \
        }                                                               \
    } while (0)

#define DEST_EA(env, insn, opsize, val, addrp) do {                     \
        TCGv ea_result = gen_ea(env, s, insn, opsize, val, addrp,       \
                                EA_STORE, IS_USER(s));                  \
        if (IS_NULL_QREG(ea_result)) {                                  \
            gen_addr_fault(s);                                          \
            return;                                                     \
        }                                                               \
    } while (0)

static inline bool use_goto_tb(DisasContext *s, uint32_t dest)
{
#ifndef CONFIG_USER_ONLY
    return (s->base.pc_first & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK)
        || (s->base.pc_next & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK);
#else
    return true;
#endif
}

/* Generate a jump to an immediate address.  */
static void gen_jmp_tb(DisasContext *s, int n, uint32_t dest)
{
    if (unlikely(s->base.singlestep_enabled)) {
        gen_exception(s, dest, EXCP_DEBUG);
    } else if (use_goto_tb(s, dest)) {
        tcg_gen_goto_tb(n);
        tcg_gen_movi_i32(QREG_PC, dest);
        tcg_gen_exit_tb(s->base.tb, n);
    } else {
        gen_jmp_im(s, dest);
        tcg_gen_exit_tb(NULL, 0);
    }
    s->base.is_jmp = DISAS_NORETURN;
}

DISAS_INSN(scc)
{
    DisasCompare c;
    int cond;
    TCGv tmp;

    cond = (insn >> 8) & 0xf;
    gen_cc_cond(&c, s, cond);

    tmp = tcg_temp_new();
    tcg_gen_setcond_i32(c.tcond, tmp, c.v1, c.v2);
    free_cond(&c);

    tcg_gen_neg_i32(tmp, tmp);
    DEST_EA(env, insn, OS_BYTE, tmp, NULL);
    tcg_temp_free(tmp);
}

DISAS_INSN(dbcc)
{
    TCGLabel *l1;
    TCGv reg;
    TCGv tmp;
    int16_t offset;
    uint32_t base;

    reg = DREG(insn, 0);
    base = s->pc;
    offset = (int16_t)read_im16(env, s);
    l1 = gen_new_label();
    gen_jmpcc(s, (insn >> 8) & 0xf, l1);

    tmp = tcg_temp_new();
    tcg_gen_ext16s_i32(tmp, reg);
    tcg_gen_addi_i32(tmp, tmp, -1);
    gen_partset_reg(OS_WORD, reg, tmp);
    tcg_gen_brcondi_i32(TCG_COND_EQ, tmp, -1, l1);
    gen_jmp_tb(s, 1, base + offset);
    gen_set_label(l1);
    gen_jmp_tb(s, 0, s->pc);
}

DISAS_INSN(undef_mac)
{
    gen_exception(s, s->base.pc_next, EXCP_LINEA);
}

DISAS_INSN(undef_fpu)
{
    gen_exception(s, s->base.pc_next, EXCP_LINEF);
}

DISAS_INSN(undef)
{
    /*
     * ??? This is both instructions that are as yet unimplemented
     * for the 680x0 series, as well as those that are implemented
     * but actually illegal for CPU32 or pre-68020.
     */
    qemu_log_mask(LOG_UNIMP, "Illegal instruction: %04x @ %08x\n",
                  insn, s->base.pc_next);
    gen_exception(s, s->base.pc_next, EXCP_ILLEGAL);
}

DISAS_INSN(mulw)
{
    TCGv reg;
    TCGv tmp;
    TCGv src;
    int sign;

    sign = (insn & 0x100) != 0;
    reg = DREG(insn, 9);
    tmp = tcg_temp_new();
    if (sign)
        tcg_gen_ext16s_i32(tmp, reg);
    else
        tcg_gen_ext16u_i32(tmp, reg);
    SRC_EA(env, src, OS_WORD, sign, NULL);
    tcg_gen_mul_i32(tmp, tmp, src);
    tcg_gen_mov_i32(reg, tmp);
    gen_logic_cc(s, tmp, OS_LONG);
    tcg_temp_free(tmp);
}

DISAS_INSN(divw)
{
    int sign;
    TCGv src;
    TCGv destr;

    /* divX.w <EA>,Dn    32/16 -> 16r:16q */

    sign = (insn & 0x100) != 0;

    /* dest.l / src.w */

    SRC_EA(env, src, OS_WORD, sign, NULL);
    destr = tcg_const_i32(REG(insn, 9));
    if (sign) {
        gen_helper_divsw(cpu_env, destr, src);
    } else {
        gen_helper_divuw(cpu_env, destr, src);
    }
    tcg_temp_free(destr);

    set_cc_op(s, CC_OP_FLAGS);
}

DISAS_INSN(divl)
{
    TCGv num, reg, den;
    int sign;
    uint16_t ext;

    ext = read_im16(env, s);

    sign = (ext & 0x0800) != 0;

    if (ext & 0x400) {
        if (!m68k_feature(s->env, M68K_FEATURE_QUAD_MULDIV)) {
            gen_exception(s, s->base.pc_next, EXCP_ILLEGAL);
            return;
        }

        /* divX.l <EA>, Dr:Dq    64/32 -> 32r:32q */

        SRC_EA(env, den, OS_LONG, 0, NULL);
        num = tcg_const_i32(REG(ext, 12));
        reg = tcg_const_i32(REG(ext, 0));
        if (sign) {
            gen_helper_divsll(cpu_env, num, reg, den);
        } else {
            gen_helper_divull(cpu_env, num, reg, den);
        }
        tcg_temp_free(reg);
        tcg_temp_free(num);
        set_cc_op(s, CC_OP_FLAGS);
        return;
    }

    /* divX.l <EA>, Dq        32/32 -> 32q     */
    /* divXl.l <EA>, Dr:Dq    32/32 -> 32r:32q */

    SRC_EA(env, den, OS_LONG, 0, NULL);
    num = tcg_const_i32(REG(ext, 12));
    reg = tcg_const_i32(REG(ext, 0));
    if (sign) {
        gen_helper_divsl(cpu_env, num, reg, den);
    } else {
        gen_helper_divul(cpu_env, num, reg, den);
    }
    tcg_temp_free(reg);
    tcg_temp_free(num);

    set_cc_op(s, CC_OP_FLAGS);
}

static void bcd_add(TCGv dest, TCGv src)
{
    TCGv t0, t1;

    /*
     * dest10 = dest10 + src10 + X
     *
     *        t1 = src
     *        t2 = t1 + 0x066
     *        t3 = t2 + dest + X
     *        t4 = t2 ^ dest
     *        t5 = t3 ^ t4
     *        t6 = ~t5 & 0x110
     *        t7 = (t6 >> 2) | (t6 >> 3)
     *        return t3 - t7
     */

    /*
     * t1 = (src + 0x066) + dest + X
     *    = result with some possible exceding 0x6
     */

    t0 = tcg_const_i32(0x066);
    tcg_gen_add_i32(t0, t0, src);

    t1 = tcg_temp_new();
    tcg_gen_add_i32(t1, t0, dest);
    tcg_gen_add_i32(t1, t1, QREG_CC_X);

    /* we will remove exceding 0x6 where there is no carry */

    /*
     * t0 = (src + 0x0066) ^ dest
     *    = t1 without carries
     */

    tcg_gen_xor_i32(t0, t0, dest);

    /*
     * extract the carries
     * t0 = t0 ^ t1
     *    = only the carries
     */

    tcg_gen_xor_i32(t0, t0, t1);

    /*
     * generate 0x1 where there is no carry
     * and for each 0x10, generate a 0x6
     */

    tcg_gen_shri_i32(t0, t0, 3);
    tcg_gen_not_i32(t0, t0);
    tcg_gen_andi_i32(t0, t0, 0x22);
    tcg_gen_add_i32(dest, t0, t0);
    tcg_gen_add_i32(dest, dest, t0);
    tcg_temp_free(t0);

    /*
     * remove the exceding 0x6
     * for digits that have not generated a carry
     */

    tcg_gen_sub_i32(dest, t1, dest);
    tcg_temp_free(t1);
}

static void bcd_sub(TCGv dest, TCGv src)
{
    TCGv t0, t1, t2;

    /*
     *  dest10 = dest10 - src10 - X
     *         = bcd_add(dest + 1 - X, 0x199 - src)
     */

    /* t0 = 0x066 + (0x199 - src) */

    t0 = tcg_temp_new();
    tcg_gen_subfi_i32(t0, 0x1ff, src);

    /* t1 = t0 + dest + 1 - X*/

    t1 = tcg_temp_new();
    tcg_gen_add_i32(t1, t0, dest);
    tcg_gen_addi_i32(t1, t1, 1);
    tcg_gen_sub_i32(t1, t1, QREG_CC_X);

    /* t2 = t0 ^ dest */

    t2 = tcg_temp_new();
    tcg_gen_xor_i32(t2, t0, dest);

    /* t0 = t1 ^ t2 */

    tcg_gen_xor_i32(t0, t1, t2);

    /*
     * t2 = ~t0 & 0x110
     * t0 = (t2 >> 2) | (t2 >> 3)
     *
     * to fit on 8bit operands, changed in:
     *
     * t2 = ~(t0 >> 3) & 0x22
     * t0 = t2 + t2
     * t0 = t0 + t2
     */

    tcg_gen_shri_i32(t2, t0, 3);
    tcg_gen_not_i32(t2, t2);
    tcg_gen_andi_i32(t2, t2, 0x22);
    tcg_gen_add_i32(t0, t2, t2);
    tcg_gen_add_i32(t0, t0, t2);
    tcg_temp_free(t2);

    /* return t1 - t0 */

    tcg_gen_sub_i32(dest, t1, t0);
    tcg_temp_free(t0);
    tcg_temp_free(t1);
}

static void bcd_flags(TCGv val)
{
    tcg_gen_andi_i32(QREG_CC_C, val, 0x0ff);
    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_C);

    tcg_gen_extract_i32(QREG_CC_C, val, 8, 1);

    tcg_gen_mov_i32(QREG_CC_X, QREG_CC_C);
}

DISAS_INSN(abcd_reg)
{
    TCGv src;
    TCGv dest;

    gen_flush_flags(s); /* !Z is sticky */

    src = gen_extend(s, DREG(insn, 0), OS_BYTE, 0);
    dest = gen_extend(s, DREG(insn, 9), OS_BYTE, 0);
    bcd_add(dest, src);
    gen_partset_reg(OS_BYTE, DREG(insn, 9), dest);

    bcd_flags(dest);
}

DISAS_INSN(abcd_mem)
{
    TCGv src, dest, addr;

    gen_flush_flags(s); /* !Z is sticky */

    /* Indirect pre-decrement load (mode 4) */

    src = gen_ea_mode(env, s, 4, REG(insn, 0), OS_BYTE,
                      NULL_QREG, NULL, EA_LOADU, IS_USER(s));
    dest = gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE,
                       NULL_QREG, &addr, EA_LOADU, IS_USER(s));

    bcd_add(dest, src);

    gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE, dest, &addr,
                EA_STORE, IS_USER(s));

    bcd_flags(dest);
}

DISAS_INSN(sbcd_reg)
{
    TCGv src, dest;

    gen_flush_flags(s); /* !Z is sticky */

    src = gen_extend(s, DREG(insn, 0), OS_BYTE, 0);
    dest = gen_extend(s, DREG(insn, 9), OS_BYTE, 0);

    bcd_sub(dest, src);

    gen_partset_reg(OS_BYTE, DREG(insn, 9), dest);

    bcd_flags(dest);
}

DISAS_INSN(sbcd_mem)
{
    TCGv src, dest, addr;

    gen_flush_flags(s); /* !Z is sticky */

    /* Indirect pre-decrement load (mode 4) */

    src = gen_ea_mode(env, s, 4, REG(insn, 0), OS_BYTE,
                      NULL_QREG, NULL, EA_LOADU, IS_USER(s));
    dest = gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE,
                       NULL_QREG, &addr, EA_LOADU, IS_USER(s));

    bcd_sub(dest, src);

    gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE, dest, &addr,
                EA_STORE, IS_USER(s));

    bcd_flags(dest);
}

DISAS_INSN(nbcd)
{
    TCGv src, dest;
    TCGv addr;

    gen_flush_flags(s); /* !Z is sticky */

    SRC_EA(env, src, OS_BYTE, 0, &addr);

    dest = tcg_const_i32(0);
    bcd_sub(dest, src);

    DEST_EA(env, insn, OS_BYTE, dest, &addr);

    bcd_flags(dest);

    tcg_temp_free(dest);
}

DISAS_INSN(addsub)
{
    TCGv reg;
    TCGv dest;
    TCGv src;
    TCGv tmp;
    TCGv addr;
    int add;
    int opsize;

    add = (insn & 0x4000) != 0;
    opsize = insn_opsize(insn);
    reg = gen_extend(s, DREG(insn, 9), opsize, 1);
    dest = tcg_temp_new();
    if (insn & 0x100) {
        SRC_EA(env, tmp, opsize, 1, &addr);
        src = reg;
    } else {
        tmp = reg;
        SRC_EA(env, src, opsize, 1, NULL);
    }
    if (add) {
        tcg_gen_add_i32(dest, tmp, src);
        tcg_gen_setcond_i32(TCG_COND_LTU, QREG_CC_X, dest, src);
        set_cc_op(s, CC_OP_ADDB + opsize);
    } else {
        tcg_gen_setcond_i32(TCG_COND_LTU, QREG_CC_X, tmp, src);
        tcg_gen_sub_i32(dest, tmp, src);
        set_cc_op(s, CC_OP_SUBB + opsize);
    }
    gen_update_cc_add(dest, src, opsize);
    if (insn & 0x100) {
        DEST_EA(env, insn, opsize, dest, &addr);
    } else {
        gen_partset_reg(opsize, DREG(insn, 9), dest);
    }
    tcg_temp_free(dest);
}

/* Reverse the order of the bits in REG.  */
DISAS_INSN(bitrev)
{
    TCGv reg;
    reg = DREG(insn, 0);
    gen_helper_bitrev(reg, reg);
}

DISAS_INSN(bitop_reg)
{
    int opsize;
    int op;
    TCGv src1;
    TCGv src2;
    TCGv tmp;
    TCGv addr;
    TCGv dest;

    if ((insn & 0x38) != 0)
        opsize = OS_BYTE;
    else
        opsize = OS_LONG;
    op = (insn >> 6) & 3;
    SRC_EA(env, src1, opsize, 0, op ? &addr: NULL);

    gen_flush_flags(s);
    src2 = tcg_temp_new();
    if (opsize == OS_BYTE)
        tcg_gen_andi_i32(src2, DREG(insn, 9), 7);
    else
        tcg_gen_andi_i32(src2, DREG(insn, 9), 31);

    tmp = tcg_const_i32(1);
    tcg_gen_shl_i32(tmp, tmp, src2);
    tcg_temp_free(src2);

    tcg_gen_and_i32(QREG_CC_Z, src1, tmp);

    dest = tcg_temp_new();
    switch (op) {
    case 1: /* bchg */
        tcg_gen_xor_i32(dest, src1, tmp);
        break;
    case 2: /* bclr */
        tcg_gen_andc_i32(dest, src1, tmp);
        break;
    case 3: /* bset */
        tcg_gen_or_i32(dest, src1, tmp);
        break;
    default: /* btst */
        break;
    }
    tcg_temp_free(tmp);
    if (op) {
        DEST_EA(env, insn, opsize, dest, &addr);
    }
    tcg_temp_free(dest);
}

DISAS_INSN(sats)
{
    TCGv reg;
    reg = DREG(insn, 0);

    gen_flush_flags(s);
    gen_helper_sats(reg, reg, QREG_CC_V);
    gen_logic_cc(s, reg, OS_LONG);
}

static void gen_push(DisasContext *s, TCGv val)
{
    TCGv tmp;

    tmp = tcg_temp_new();
    tcg_gen_subi_i32(tmp, QREG_SP, 4);
    gen_store(s, OS_LONG, tmp, val, IS_USER(s));
    tcg_gen_mov_i32(QREG_SP, tmp);
    tcg_temp_free(tmp);
}

static TCGv mreg(int reg)
{
    if (reg < 8) {
        /* Dx */
        return cpu_dregs[reg];
    }
    /* Ax */
    return cpu_aregs[reg & 7];
}

DISAS_INSN(movem)
{
    TCGv addr, incr, tmp, r[16];
    int is_load = (insn & 0x0400) != 0;
    int opsize = (insn & 0x40) != 0 ? OS_LONG : OS_WORD;
    uint16_t mask = read_im16(env, s);
    int mode = extract32(insn, 3, 3);
    int reg0 = REG(insn, 0);
    int i;

    tmp = cpu_aregs[reg0];

    switch (mode) {
    case 0: /* data register direct */
    case 1: /* addr register direct */
    do_addr_fault:
        gen_addr_fault(s);
        return;

    case 2: /* indirect */
        break;

    case 3: /* indirect post-increment */
        if (!is_load) {
            /* post-increment is not allowed */
            goto do_addr_fault;
        }
        break;

    case 4: /* indirect pre-decrement */
        if (is_load) {
            /* pre-decrement is not allowed */
            goto do_addr_fault;
        }
        /*
         * We want a bare copy of the address reg, without any pre-decrement
         * adjustment, as gen_lea would provide.
         */
        break;

    default:
        tmp = gen_lea_mode(env, s, mode, reg0, opsize);
        if (IS_NULL_QREG(tmp)) {
            goto do_addr_fault;
        }
        break;
    }

    addr = tcg_temp_new();
    tcg_gen_mov_i32(addr, tmp);
    incr = tcg_const_i32(opsize_bytes(opsize));

    if (is_load) {
        /* memory to register */
        for (i = 0; i < 16; i++) {
            if (mask & (1 << i)) {
                r[i] = gen_load(s, opsize, addr, 1, IS_USER(s));
                tcg_gen_add_i32(addr, addr, incr);
            }
        }
        for (i = 0; i < 16; i++) {
            if (mask & (1 << i)) {
                tcg_gen_mov_i32(mreg(i), r[i]);
                tcg_temp_free(r[i]);
            }
        }
        if (mode == 3) {
            /* post-increment: movem (An)+,X */
            tcg_gen_mov_i32(cpu_aregs[reg0], addr);
        }
    } else {
        /* register to memory */
        if (mode == 4) {
            /* pre-decrement: movem X,-(An) */
            for (i = 15; i >= 0; i--) {
                if ((mask << i) & 0x8000) {
                    tcg_gen_sub_i32(addr, addr, incr);
                    if (reg0 + 8 == i &&
                        m68k_feature(s->env, M68K_FEATURE_EXT_FULL)) {
                        /*
                         * M68020+: if the addressing register is the
                         * register moved to memory, the value written
                         * is the initial value decremented by the size of
                         * the operation, regardless of how many actual
                         * stores have been performed until this point.
                         * M68000/M68010: the value is the initial value.
                         */
                        tmp = tcg_temp_new();
                        tcg_gen_sub_i32(tmp, cpu_aregs[reg0], incr);
                        gen_store(s, opsize, addr, tmp, IS_USER(s));
                        tcg_temp_free(tmp);
                    } else {
                        gen_store(s, opsize, addr, mreg(i), IS_USER(s));
                    }
                }
            }
            tcg_gen_mov_i32(cpu_aregs[reg0], addr);
        } else {
            for (i = 0; i < 16; i++) {
                if (mask & (1 << i)) {
                    gen_store(s, opsize, addr, mreg(i), IS_USER(s));
                    tcg_gen_add_i32(addr, addr, incr);
                }
            }
        }
    }

    tcg_temp_free(incr);
    tcg_temp_free(addr);
}

DISAS_INSN(movep)
{
    uint8_t i;
    int16_t displ;
    TCGv reg;
    TCGv addr;
    TCGv abuf;
    TCGv dbuf;

    displ = read_im16(env, s);

    addr = AREG(insn, 0);
    reg = DREG(insn, 9);

    abuf = tcg_temp_new();
    tcg_gen_addi_i32(abuf, addr, displ);
    dbuf = tcg_temp_new();

    if (insn & 0x40) {
        i = 4;
    } else {
        i = 2;
    }

    if (insn & 0x80) {
        for ( ; i > 0 ; i--) {
            tcg_gen_shri_i32(dbuf, reg, (i - 1) * 8);
            tcg_gen_qemu_st8(dbuf, abuf, IS_USER(s));
            if (i > 1) {
                tcg_gen_addi_i32(abuf, abuf, 2);
            }
        }
    } else {
        for ( ; i > 0 ; i--) {
            tcg_gen_qemu_ld8u(dbuf, abuf, IS_USER(s));
            tcg_gen_deposit_i32(reg, reg, dbuf, (i - 1) * 8, 8);
            if (i > 1) {
                tcg_gen_addi_i32(abuf, abuf, 2);
            }
        }
    }
    tcg_temp_free(abuf);
    tcg_temp_free(dbuf);
}

DISAS_INSN(bitop_im)
{
    int opsize;
    int op;
    TCGv src1;
    uint32_t mask;
    int bitnum;
    TCGv tmp;
    TCGv addr;

    if ((insn & 0x38) != 0)
        opsize = OS_BYTE;
    else
        opsize = OS_LONG;
    op = (insn >> 6) & 3;

    bitnum = read_im16(env, s);
    if (m68k_feature(s->env, M68K_FEATURE_M68000)) {
        if (bitnum & 0xfe00) {
            disas_undef(env, s, insn);
            return;
        }
    } else {
        if (bitnum & 0xff00) {
            disas_undef(env, s, insn);
            return;
        }
    }

    SRC_EA(env, src1, opsize, 0, op ? &addr: NULL);

    gen_flush_flags(s);
    if (opsize == OS_BYTE)
        bitnum &= 7;
    else
        bitnum &= 31;
    mask = 1 << bitnum;

   tcg_gen_andi_i32(QREG_CC_Z, src1, mask);

    if (op) {
        tmp = tcg_temp_new();
        switch (op) {
        case 1: /* bchg */
            tcg_gen_xori_i32(tmp, src1, mask);
            break;
        case 2: /* bclr */
            tcg_gen_andi_i32(tmp, src1, ~mask);
            break;
        case 3: /* bset */
            tcg_gen_ori_i32(tmp, src1, mask);
            break;
        default: /* btst */
            break;
        }
        DEST_EA(env, insn, opsize, tmp, &addr);
        tcg_temp_free(tmp);
    }
}

static TCGv gen_get_ccr(DisasContext *s)
{
    TCGv dest;

    update_cc_op(s);
    dest = tcg_temp_new();
    gen_helper_get_ccr(dest, cpu_env);
    return dest;
}

static TCGv gen_get_sr(DisasContext *s)
{
    TCGv ccr;
    TCGv sr;

    ccr = gen_get_ccr(s);
    sr = tcg_temp_new();
    tcg_gen_andi_i32(sr, QREG_SR, 0xffe0);
    tcg_gen_or_i32(sr, sr, ccr);
    tcg_temp_free(ccr);
    return sr;
}

static void gen_set_sr_im(DisasContext *s, uint16_t val, int ccr_only)
{
    if (ccr_only) {
        tcg_gen_movi_i32(QREG_CC_C, val & CCF_C ? 1 : 0);
        tcg_gen_movi_i32(QREG_CC_V, val & CCF_V ? -1 : 0);
        tcg_gen_movi_i32(QREG_CC_Z, val & CCF_Z ? 0 : 1);
        tcg_gen_movi_i32(QREG_CC_N, val & CCF_N ? -1 : 0);
        tcg_gen_movi_i32(QREG_CC_X, val & CCF_X ? 1 : 0);
    } else {
        TCGv sr = tcg_const_i32(val);
        gen_helper_set_sr(cpu_env, sr);
        tcg_temp_free(sr);
    }
    set_cc_op(s, CC_OP_FLAGS);
}

static void gen_set_sr(DisasContext *s, TCGv val, int ccr_only)
{
    if (ccr_only) {
        gen_helper_set_ccr(cpu_env, val);
    } else {
        gen_helper_set_sr(cpu_env, val);
    }
    set_cc_op(s, CC_OP_FLAGS);
}

static void gen_move_to_sr(CPUM68KState *env, DisasContext *s, uint16_t insn,
                           bool ccr_only)
{
    if ((insn & 0x3f) == 0x3c) {
        uint16_t val;
        val = read_im16(env, s);
        gen_set_sr_im(s, val, ccr_only);
    } else {
        TCGv src;
        SRC_EA(env, src, OS_WORD, 0, NULL);
        gen_set_sr(s, src, ccr_only);
    }
}

DISAS_INSN(arith_im)
{
    int op;
    TCGv im;
    TCGv src1;
    TCGv dest;
    TCGv addr;
    int opsize;
    bool with_SR = ((insn & 0x3f) == 0x3c);

    op = (insn >> 9) & 7;
    opsize = insn_opsize(insn);
    switch (opsize) {
    case OS_BYTE:
        im = tcg_const_i32((int8_t)read_im8(env, s));
        break;
    case OS_WORD:
        im = tcg_const_i32((int16_t)read_im16(env, s));
        break;
    case OS_LONG:
        im = tcg_const_i32(read_im32(env, s));
        break;
    default:
        g_assert_not_reached();
    }

    if (with_SR) {
        /* SR/CCR can only be used with andi/eori/ori */
        if (op == 2 || op == 3 || op == 6) {
            disas_undef(env, s, insn);
            return;
        }
        switch (opsize) {
        case OS_BYTE:
            src1 = gen_get_ccr(s);
            break;
        case OS_WORD:
            if (IS_USER(s)) {
                gen_exception(s, s->base.pc_next, EXCP_PRIVILEGE);
                return;
            }
            src1 = gen_get_sr(s);
            break;
        default:
            /* OS_LONG; others already g_assert_not_reached.  */
            disas_undef(env, s, insn);
            return;
        }
    } else {
        SRC_EA(env, src1, opsize, 1, (op == 6) ? NULL : &addr);
    }
    dest = tcg_temp_new();
    switch (op) {
    case 0: /* ori */
        tcg_gen_or_i32(dest, src1, im);
        if (with_SR) {
            gen_set_sr(s, dest, opsize == OS_BYTE);
        } else {
            DEST_EA(env, insn, opsize, dest, &addr);
            gen_logic_cc(s, dest, opsize);
        }
        break;
    case 1: /* andi */
        tcg_gen_and_i32(dest, src1, im);
        if (with_SR) {
            gen_set_sr(s, dest, opsize == OS_BYTE);
        } else {
            DEST_EA(env, insn, opsize, dest, &addr);
            gen_logic_cc(s, dest, opsize);
        }
        break;
    case 2: /* subi */
        tcg_gen_setcond_i32(TCG_COND_LTU, QREG_CC_X, src1, im);
        tcg_gen_sub_i32(dest, src1, im);
        gen_update_cc_add(dest, im, opsize);
        set_cc_op(s, CC_OP_SUBB + opsize);
        DEST_EA(env, insn, opsize, dest, &addr);
        break;
    case 3: /* addi */
        tcg_gen_add_i32(dest, src1, im);
        gen_update_cc_add(dest, im, opsize);
        tcg_gen_setcond_i32(TCG_COND_LTU, QREG_CC_X, dest, im);
        set_cc_op(s, CC_OP_ADDB + opsize);
        DEST_EA(env, insn, opsize, dest, &addr);
        break;
    case 5: /* eori */
        tcg_gen_xor_i32(dest, src1, im);
        if (with_SR) {
            gen_set_sr(s, dest, opsize == OS_BYTE);
        } else {
            DEST_EA(env, insn, opsize, dest, &addr);
            gen_logic_cc(s, dest, opsize);
        }
        break;
    case 6: /* cmpi */
        gen_update_cc_cmp(s, src1, im, opsize);
        break;
    default:
        abort();
    }
    tcg_temp_free(im);
    tcg_temp_free(dest);
}

DISAS_INSN(cas)
{
    int opsize;
    TCGv addr;
    uint16_t ext;
    TCGv load;
    TCGv cmp;
    TCGMemOp opc;

    switch ((insn >> 9) & 3) {
    case 1:
        opsize = OS_BYTE;
        opc = MO_SB;
        break;
    case 2:
        opsize = OS_WORD;
        opc = MO_TESW;
        break;
    case 3:
        opsize = OS_LONG;
        opc = MO_TESL;
        break;
    default:
        g_assert_not_reached();
    }

    ext = read_im16(env, s);

    /* cas Dc,Du,<EA> */

    addr = gen_lea(env, s, insn, opsize);
    if (IS_NULL_QREG(addr)) {
        gen_addr_fault(s);
        return;
    }

    cmp = gen_extend(s, DREG(ext, 0), opsize, 1);

    /*
     * if  <EA> == Dc then
     *     <EA> = Du
     *     Dc = <EA> (because <EA> == Dc)
     * else
     *     Dc = <EA>
     */

    load = tcg_temp_new();
    tcg_gen_atomic_cmpxchg_i32(load, addr, cmp, DREG(ext, 6),
                               IS_USER(s), opc);
    /* update flags before setting cmp to load */
    gen_update_cc_cmp(s, load, cmp, opsize);
    gen_partset_reg(opsize, DREG(ext, 0), load);

    tcg_temp_free(load);

    switch (extract32(insn, 3, 3)) {
    case 3: /* Indirect postincrement.  */
        tcg_gen_addi_i32(AREG(insn, 0), addr, opsize_bytes(opsize));
        break;
    case 4: /* Indirect predecrememnt.  */
        tcg_gen_mov_i32(AREG(insn, 0), addr);
        break;
    }
}

DISAS_INSN(cas2w)
{
    uint16_t ext1, ext2;
    TCGv addr1, addr2;
    TCGv regs;

    /* cas2 Dc1:Dc2,Du1:Du2,(Rn1):(Rn2) */

    ext1 = read_im16(env, s);

    if (ext1 & 0x8000) {
        /* Address Register */
        addr1 = AREG(ext1, 12);
    } else {
        /* Data Register */
        addr1 = DREG(ext1, 12);
    }

    ext2 = read_im16(env, s);
    if (ext2 & 0x8000) {
        /* Address Register */
        addr2 = AREG(ext2, 12);
    } else {
        /* Data Register */
        addr2 = DREG(ext2, 12);
    }

    /*
     * if (R1) == Dc1 && (R2) == Dc2 then
     *     (R1) = Du1
     *     (R2) = Du2
     * else
     *     Dc1 = (R1)
     *     Dc2 = (R2)
     */

    regs = tcg_const_i32(REG(ext2, 6) |
                         (REG(ext1, 6) << 3) |
                         (REG(ext2, 0) << 6) |
                         (REG(ext1, 0) << 9));
    if (tb_cflags(s->base.tb) & CF_PARALLEL) {
        gen_helper_exit_atomic(cpu_env);
    } else {
        gen_helper_cas2w(cpu_env, regs, addr1, addr2);
    }
    tcg_temp_free(regs);

    /* Note that cas2w also assigned to env->cc_op.  */
    s->cc_op = CC_OP_CMPW;
    s->cc_op_synced = 1;
}

DISAS_INSN(cas2l)
{
    uint16_t ext1, ext2;
    TCGv addr1, addr2, regs;

    /* cas2 Dc1:Dc2,Du1:Du2,(Rn1):(Rn2) */

    ext1 = read_im16(env, s);

    if (ext1 & 0x8000) {
        /* Address Register */
        addr1 = AREG(ext1, 12);
    } else {
        /* Data Register */
        addr1 = DREG(ext1, 12);
    }

    ext2 = read_im16(env, s);
    if (ext2 & 0x8000) {
        /* Address Register */
        addr2 = AREG(ext2, 12);
    } else {
        /* Data Register */
        addr2 = DREG(ext2, 12);
    }

    /*
     * if (R1) == Dc1 && (R2) == Dc2 then
     *     (R1) = Du1
     *     (R2) = Du2
     * else
     *     Dc1 = (R1)
     *     Dc2 = (R2)
     */

    regs = tcg_const_i32(REG(ext2, 6) |
                         (REG(ext1, 6) << 3) |
                         (REG(ext2, 0) << 6) |
                         (REG(ext1, 0) << 9));
    if (tb_cflags(s->base.tb) & CF_PARALLEL) {
        gen_helper_cas2l_parallel(cpu_env, regs, addr1, addr2);
    } else {
        gen_helper_cas2l(cpu_env, regs, addr1, addr2);
    }
    tcg_temp_free(regs);

    /* Note that cas2l also assigned to env->cc_op.  */
    s->cc_op = CC_OP_CMPL;
    s->cc_op_synced = 1;
}

DISAS_INSN(byterev)
{
    TCGv reg;

    reg = DREG(insn, 0);
    tcg_gen_bswap32_i32(reg, reg);
}

DISAS_INSN(move)
{
    TCGv src;
    TCGv dest;
    int op;
    int opsize;

    switch (insn >> 12) {
    case 1: /* move.b */
        opsize = OS_BYTE;
        break;
    case 2: /* move.l */
        opsize = OS_LONG;
        break;
    case 3: /* move.w */
        opsize = OS_WORD;
        break;
    default:
        abort();
    }
    SRC_EA(env, src, opsize, 1, NULL);
    op = (insn >> 6) & 7;
    if (op == 1) {
        /* movea */
        /* The value will already have been sign extended.  */
        dest = AREG(insn, 9);
        tcg_gen_mov_i32(dest, src);
    } else {
        /* normal move */
        uint16_t dest_ea;
        dest_ea = ((insn >> 9) & 7) | (op << 3);
        DEST_EA(env, dest_ea, opsize, src, NULL);
        /* This will be correct because loads sign extend.  */
        gen_logic_cc(s, src, opsize);
    }
}

DISAS_INSN(negx)
{
    TCGv z;
    TCGv src;
    TCGv addr;
    int opsize;

    opsize = insn_opsize(insn);
    SRC_EA(env, src, opsize, 1, &addr);

    gen_flush_flags(s); /* compute old Z */

    /*
     * Perform substract with borrow.
     * (X, N) =  -(src + X);
     */

    z = tcg_const_i32(0);
    tcg_gen_add2_i32(QREG_CC_N, QREG_CC_X, src, z, QREG_CC_X, z);
    tcg_gen_sub2_i32(QREG_CC_N, QREG_CC_X, z, z, QREG_CC_N, QREG_CC_X);
    tcg_temp_free(z);
    gen_ext(QREG_CC_N, QREG_CC_N, opsize, 1);

    tcg_gen_andi_i32(QREG_CC_X, QREG_CC_X, 1);

    /*
     * Compute signed-overflow for negation.  The normal formula for
     * subtraction is (res ^ src) & (src ^ dest), but with dest==0
     * this simplies to res & src.
     */

    tcg_gen_and_i32(QREG_CC_V, QREG_CC_N, src);

    /* Copy the rest of the results into place.  */
    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_N); /* !Z is sticky */
    tcg_gen_mov_i32(QREG_CC_C, QREG_CC_X);

    set_cc_op(s, CC_OP_FLAGS);

    /* result is in QREG_CC_N */

    DEST_EA(env, insn, opsize, QREG_CC_N, &addr);
}

DISAS_INSN(lea)
{
    TCGv reg;
    TCGv tmp;

    reg = AREG(insn, 9);
    tmp = gen_lea(env, s, insn, OS_LONG);
    if (IS_NULL_QREG(tmp)) {
        gen_addr_fault(s);
        return;
    }
    tcg_gen_mov_i32(reg, tmp);
}

DISAS_INSN(clr)
{
    int opsize;
    TCGv zero;

    zero = tcg_const_i32(0);

    opsize = insn_opsize(insn);
    DEST_EA(env, insn, opsize, zero, NULL);
    gen_logic_cc(s, zero, opsize);
    tcg_temp_free(zero);
}

DISAS_INSN(move_from_ccr)
{
    TCGv ccr;

    ccr = gen_get_ccr(s);
    DEST_EA(env, insn, OS_WORD, ccr, NULL);
}

DISAS_INSN(neg)
{
    TCGv src1;
    TCGv dest;
    TCGv addr;
    int opsize;

    opsize = insn_opsize(insn);
    SRC_EA(env, src1, opsize, 1, &addr);
    dest = tcg_temp_new();
    tcg_gen_neg_i32(dest, src1);
    set_cc_op(s, CC_OP_SUBB + opsize);
    gen_update_cc_add(dest, src1, opsize);
    tcg_gen_setcondi_i32(TCG_COND_NE, QREG_CC_X, dest, 0);
    DEST_EA(env, insn, opsize, dest, &addr);
    tcg_temp_free(dest);
}

DISAS_INSN(move_to_ccr)
{
    gen_move_to_sr(env, s, insn, true);
}

DISAS_INSN(not)
{
    TCGv src1;
    TCGv dest;
    TCGv addr;
    int opsize;

    opsize = insn_opsize(insn);
    SRC_EA(env, src1, opsize, 1, &addr);
    dest = tcg_temp_new();
    tcg_gen_not_i32(dest, src1);
    DEST_EA(env, insn, opsize, dest, &addr);
    gen_logic_cc(s, dest, opsize);
}

DISAS_INSN(swap)
{
    TCGv src1;
    TCGv src2;
    TCGv reg;

    src1 = tcg_temp_new();
    src2 = tcg_temp_new();
    reg = DREG(insn, 0);
    tcg_gen_shli_i32(src1, reg, 16);
    tcg_gen_shri_i32(src2, reg, 16);
    tcg_gen_or_i32(reg, src1, src2);
    tcg_temp_free(src2);
    tcg_temp_free(src1);
    gen_logic_cc(s, reg, OS_LONG);
}

DISAS_INSN(bkpt)
{
    gen_exception(s, s->base.pc_next, EXCP_DEBUG);
}

DISAS_INSN(pea)
{
    TCGv tmp;

    tmp = gen_lea(env, s, insn, OS_LONG);
    if (IS_NULL_QREG(tmp)) {
        gen_addr_fault(s);
        return;
    }
    gen_push(s, tmp);
}

DISAS_INSN(ext)
{
    int op;
    TCGv reg;
    TCGv tmp;

    reg = DREG(insn, 0);
    op = (insn >> 6) & 7;
    tmp = tcg_temp_new();
    if (op == 3)
        tcg_gen_ext16s_i32(tmp, reg);
    else
        tcg_gen_ext8s_i32(tmp, reg);
    if (op == 2)
        gen_partset_reg(OS_WORD, reg, tmp);
    else
        tcg_gen_mov_i32(reg, tmp);
    gen_logic_cc(s, tmp, OS_LONG);
    tcg_temp_free(tmp);
}

DISAS_INSN(tst)
{
    int opsize;
    TCGv tmp;

    opsize = insn_opsize(insn);
    SRC_EA(env, tmp, opsize, 1, NULL);
    gen_logic_cc(s, tmp, opsize);
}

DISAS_INSN(pulse)
{
  /* Implemented as a NOP.  */
}

DISAS_INSN(illegal)
{
    gen_exception(s, s->base.pc_next, EXCP_ILLEGAL);
}

/* ??? This should be atomic.  */
DISAS_INSN(tas)
{
    TCGv dest;
    TCGv src1;
    TCGv addr;

    dest = tcg_temp_new();
    SRC_EA(env, src1, OS_BYTE, 1, &addr);
    gen_logic_cc(s, src1, OS_BYTE);
    tcg_gen_ori_i32(dest, src1, 0x80);
    DEST_EA(env, insn, OS_BYTE, dest, &addr);
    tcg_temp_free(dest);
}

DISAS_INSN(mull)
{
    uint16_t ext;
    TCGv src1;
    int sign;

    ext = read_im16(env, s);

    sign = ext & 0x800;

    if (ext & 0x400) {
        if (!m68k_feature(s->env, M68K_FEATURE_QUAD_MULDIV)) {
            gen_exception(s, s->base.pc_next, EXCP_ILLEGAL);
            return;
        }

        SRC_EA(env, src1, OS_LONG, 0, NULL);

        if (sign) {
            tcg_gen_muls2_i32(QREG_CC_Z, QREG_CC_N, src1, DREG(ext, 12));
        } else {
            tcg_gen_mulu2_i32(QREG_CC_Z, QREG_CC_N, src1, DREG(ext, 12));
        }
        /* if Dl == Dh, 68040 returns low word */
        tcg_gen_mov_i32(DREG(ext, 0), QREG_CC_N);
        tcg_gen_mov_i32(DREG(ext, 12), QREG_CC_Z);
        tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_N);

        tcg_gen_movi_i32(QREG_CC_V, 0);
        tcg_gen_movi_i32(QREG_CC_C, 0);

        set_cc_op(s, CC_OP_FLAGS);
        return;
    }
    SRC_EA(env, src1, OS_LONG, 0, NULL);
    if (m68k_feature(s->env, M68K_FEATURE_M68000)) {
        tcg_gen_movi_i32(QREG_CC_C, 0);
        if (sign) {
            tcg_gen_muls2_i32(QREG_CC_N, QREG_CC_V, src1, DREG(ext, 12));
            /* QREG_CC_V is -(QREG_CC_V != (QREG_CC_N >> 31)) */
            tcg_gen_sari_i32(QREG_CC_Z, QREG_CC_N, 31);
            tcg_gen_setcond_i32(TCG_COND_NE, QREG_CC_V, QREG_CC_V, QREG_CC_Z);
        } else {
            tcg_gen_mulu2_i32(QREG_CC_N, QREG_CC_V, src1, DREG(ext, 12));
            /* QREG_CC_V is -(QREG_CC_V != 0), use QREG_CC_C as 0 */
            tcg_gen_setcond_i32(TCG_COND_NE, QREG_CC_V, QREG_CC_V, QREG_CC_C);
        }
        tcg_gen_neg_i32(QREG_CC_V, QREG_CC_V);
        tcg_gen_mov_i32(DREG(ext, 12), QREG_CC_N);

        tcg_gen_mov_i32(QREG_CC_Z, QREG_CC_N);

        set_cc_op(s, CC_OP_FLAGS);
    } else {
        /*
         * The upper 32 bits of the product are discarded, so
         * muls.l and mulu.l are functionally equivalent.
         */
        tcg_gen_mul_i32(DREG(ext, 12), src1, DREG(ext, 12));
        gen_logic_cc(s, DREG(ext, 12), OS_LONG);
    }
}

static void gen_link(DisasContext *s, uint16_t insn, int32_t offset)
{
    TCGv reg;
    TCGv tmp;

    reg = AREG(insn, 0);
    tmp = tcg_temp_new();
    tcg_gen_subi_i32(tmp, QREG_SP, 4);
    gen_store(s, OS_LONG, tmp, reg, IS_USER(s));
    if ((insn & 7) != 7) {
        tcg_gen_mov_i32(reg, tmp);
    }
    tcg_gen_addi_i32(QREG_SP, tmp, offset);
    tcg_temp_free(tmp);
}

DISAS_INSN(link)
{
    int16_t offset;

    offset = read_im16(env, s);
    gen_link(s, insn, offset);
}

DISAS_INSN(linkl)
{
    int32_t offset;

    offset = read_im32(env, s);
    gen_link(s, insn, offset);
}

DISAS_INSN(unlk)
{
    TCGv src;
    TCGv reg;
    TCGv tmp;

    src = tcg_temp_new();
    reg = AREG(insn, 0);
    tcg_gen_mov_i32(src, reg);
    tmp = gen_load(s, OS_LONG, src, 0, IS_USER(s));
    tcg_gen_mov_i32(reg, tmp);
    tcg_gen_addi_i32(QREG_SP, src, 4);
    tcg_temp_free(src);
    tcg_temp_free(tmp);
}

#if defined(CONFIG_SOFTMMU)
DISAS_INSN(reset)
{
    if (IS_USER(s)) {
        gen_exception(s, s->base.pc_next, EXCP_PRIVILEGE);
        return;
    }

    gen_helper_reset(cpu_env);
}
#endif

DISAS_INSN(nop)
{
}

DISAS_INSN(rtd)
{
    TCGv tmp;
    int16_t offset = read_im16(env, s);

    tmp = gen_load(s, OS_LONG, QREG_SP, 0, IS_USER(s));
    tcg_gen_addi_i32(QREG_SP, QREG_SP, offset + 4);
    gen_jmp(s, tmp);
}

DISAS_INSN(rts)
{
    TCGv tmp;

    tmp = gen_load(s, OS_LONG, QREG_SP, 0, IS_USER(s));
    tcg_gen_addi_i32(QREG_SP, QREG_SP, 4);
    gen_jmp(s, tmp);
}

DISAS_INSN(jump)
{
    TCGv tmp;

    /*
     * Load the target address first to ensure correct exception
     * behavior.
     */
    tmp = gen_lea(env, s, insn, OS_LONG);
    if (IS_NULL_QREG(tmp)) {
        gen_addr_fault(s);
        return;
    }
    if ((insn & 0x40) == 0) {
        /* jsr */
        gen_push(s, tcg_const_i32(s->pc));
    }
    gen_jmp(s, tmp);
}

DISAS_INSN(addsubq)
{
    TCGv src;
    TCGv dest;
    TCGv val;