/*

 *  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, write to the Free Software

 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA

 */

#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;

/* FIXME:  These should be removed.  */

static TCGv cpu_T[2];

static TCGv cpu_F0s, cpu_F1s;

static TCGv_i64 cpu_F0d, cpu_F1d;

#define ICOUNT_TEMP cpu_T[0]

#include "gen-icount.h"

/* initialize TCG globals.  */

void arm_translate_init(void)

{

    cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");

    cpu_T[0] = tcg_global_reg_new_i32(TCG_AREG1, "T0");

    cpu_T[1] = tcg_global_reg_new_i32(TCG_AREG2, "T1");

#define GEN_HELPER 2

#include "helpers.h"

}

/* The code generator doesn't like lots of temporaries, so maintain our own

   cache for reuse within a function.  */

#define MAX_TEMPS 8

static int num_temps;

static TCGv temps[MAX_TEMPS];

/* Allocate a temporary variable.  */

static TCGv_i32 new_tmp(void)

{

    TCGv tmp;

    if (num_temps == MAX_TEMPS)

        abort();

    if (GET_TCGV_I32(temps[num_temps]))

      return temps[num_temps++];

    tmp = tcg_temp_new_i32();

    temps[num_temps++] = tmp;

    return tmp;

}

/* Release a temporary variable.  */

static void dead_tmp(TCGv tmp)

{

    int i;

    num_temps--;

    i = num_temps;

    if (TCGV_EQUAL(temps[i], tmp))

        return;

    /* Shuffle this temp to the last slot.  */

    while (!TCGV_EQUAL(temps[i], tmp))

        i--;

    while (i < num_temps) {

        temps[i] = temps[i + 1];

        i++;

    }

    temps[i] = tmp;

}

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_ld_i32(var, cpu_env, offsetof(CPUState, regs[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_st_i32(var, cpu_env, offsetof(CPUState, regs[reg]));

    dead_tmp(var);

}

/* Basic operations.  */

#define gen_op_movl_T0_T1() tcg_gen_mov_i32(cpu_T[0], cpu_T[1])

#define gen_op_movl_T0_im(im) tcg_gen_movi_i32(cpu_T[0], im)

#define gen_op_movl_T1_im(im) tcg_gen_movi_i32(cpu_T[1], im)

#define gen_op_addl_T1_im(im) tcg_gen_addi_i32(cpu_T[1], cpu_T[1], im)

#define gen_op_addl_T0_T1() tcg_gen_add_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_subl_T0_T1() tcg_gen_sub_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_rsbl_T0_T1() tcg_gen_sub_i32(cpu_T[0], cpu_T[1], cpu_T[0])

#define gen_op_addl_T0_T1_cc() gen_helper_add_cc(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_adcl_T0_T1_cc() gen_helper_adc_cc(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_subl_T0_T1_cc() gen_helper_sub_cc(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_sbcl_T0_T1_cc() gen_helper_sbc_cc(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_rsbl_T0_T1_cc() gen_helper_sub_cc(cpu_T[0], cpu_T[1], cpu_T[0])

#define gen_op_rscl_T0_T1_cc() gen_helper_sbc_cc(cpu_T[0], cpu_T[1], cpu_T[0])

#define gen_op_andl_T0_T1() tcg_gen_and_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_xorl_T0_T1() tcg_gen_xor_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_orl_T0_T1() tcg_gen_or_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_op_notl_T0() tcg_gen_not_i32(cpu_T[0], cpu_T[0])

#define gen_op_notl_T1() tcg_gen_not_i32(cpu_T[1], cpu_T[1])

#define gen_op_logic_T0_cc() gen_logic_CC(cpu_T[0]);

#define gen_op_logic_T1_cc() gen_logic_CC(cpu_T[1]);

#define gen_op_shll_T1_im(im) tcg_gen_shli_i32(cpu_T[1], cpu_T[1], im)

#define gen_op_shrl_T1_im(im) tcg_gen_shri_i32(cpu_T[1], cpu_T[1], im)

/* 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)

#define gen_op_mul_T0_T1() tcg_gen_mul_i32(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_set_cpsr(var, mask) gen_helper_cpsr_write(var, tcg_const_i32(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);

    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);

    return tmp1;

}

/* Unsigned 32x32->64 multiply.  */

static void gen_op_mull_T0_T1(void)

{

    TCGv_i64 tmp1 = tcg_temp_new_i64();

    TCGv_i64 tmp2 = tcg_temp_new_i64();

    tcg_gen_extu_i32_i64(tmp1, cpu_T[0]);

    tcg_gen_extu_i32_i64(tmp2, cpu_T[1]);

    tcg_gen_mul_i64(tmp1, tmp1, tmp2);

    tcg_gen_trunc_i64_i32(cpu_T[0], tmp1);

    tcg_gen_shri_i64(tmp1, tmp1, 32);

    tcg_gen_trunc_i64_i32(cpu_T[1], 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_gen_trunc_i64_i32(a, tmp1);

    tcg_gen_shri_i64(tmp1, tmp1, 32);

    tcg_gen_trunc_i64_i32(b, 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_T0_T1(void)

{

    TCGv tmp;

    gen_op_addl_T0_T1();

    tmp = load_cpu_field(CF);

    tcg_gen_add_i32(cpu_T[0], cpu_T[0], 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);

}

#define gen_sbc_T0_T1() gen_sub_carry(cpu_T[0], cpu_T[0], cpu_T[1])

#define gen_rsc_T0_T1() gen_sub_carry(cpu_T[0], cpu_T[1], cpu_T[0])

/* T0 &= ~T1.  Clobbers T1.  */

/* FIXME: Implement bic natively.  */

static inline void tcg_gen_bic_i32(TCGv dest, TCGv t0, TCGv t1)

{

    TCGv tmp = new_tmp();

    tcg_gen_not_i32(tmp, t1);

    tcg_gen_and_i32(dest, t0, tmp);

    dead_tmp(tmp);

}

static inline void gen_op_bicl_T0_T1(void)

{

    gen_op_notl_T1();

    gen_op_andl_T0_T1();

}

/* FIXME:  Implement this natively.  */

#define tcg_gen_abs_i32(t0, t1) gen_helper_abs(t0, t1)

/* FIXME:  Implement this natively.  */

static void tcg_gen_rori_i32(TCGv t0, TCGv t1, int i)

{

    TCGv tmp;

    if (i == 0)

        return;

    tmp = new_tmp();

    tcg_gen_shri_i32(tmp, t1, i);

    tcg_gen_shli_i32(t1, t1, 32 - i);

    tcg_gen_or_i32(t0, t1, tmp);

    dead_tmp(tmp);

}

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);