/*
 *  AArch64 translation
 *
 *  Copyright (c) 2013 Alexander Graf <agraf@suse.de>
 *
 * 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 "exec/exec-all.h"
#include "tcg/tcg-op.h"
#include "tcg/tcg-op-gvec.h"
#include "qemu/log.h"
#include "arm_ldst.h"
#include "translate.h"
#include "internals.h"
#include "qemu/host-utils.h"

#include "semihosting/semihost.h"
#include "exec/gen-icount.h"

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

#include "translate-a64.h"
#include "qemu/atomic128.h"

static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;

/* Load/store exclusive handling */
static TCGv_i64 cpu_exclusive_high;

static const char *regnames[] = {
    "x0", "x1", "x2", "x3", "x4", "x5", "x6", "x7",
    "x8", "x9", "x10", "x11", "x12", "x13", "x14", "x15",
    "x16", "x17", "x18", "x19", "x20", "x21", "x22", "x23",
    "x24", "x25", "x26", "x27", "x28", "x29", "lr", "sp"
};

enum a64_shift_type {
    A64_SHIFT_TYPE_LSL = 0,
    A64_SHIFT_TYPE_LSR = 1,
    A64_SHIFT_TYPE_ASR = 2,
    A64_SHIFT_TYPE_ROR = 3
};

/* Table based decoder typedefs - used when the relevant bits for decode
 * are too awkwardly scattered across the instruction (eg SIMD).
 */
typedef void AArch64DecodeFn(DisasContext *s, uint32_t insn);

typedef struct AArch64DecodeTable {
    uint32_t pattern;
    uint32_t mask;
    AArch64DecodeFn *disas_fn;
} AArch64DecodeTable;

/* initialize TCG globals.  */
void a64_translate_init(void)
{
    int i;

    cpu_pc = tcg_global_mem_new_i64(cpu_env,
                                    offsetof(CPUARMState, pc),
                                    "pc");
    for (i = 0; i < 32; i++) {
        cpu_X[i] = tcg_global_mem_new_i64(cpu_env,
                                          offsetof(CPUARMState, xregs[i]),
                                          regnames[i]);
    }

    cpu_exclusive_high = tcg_global_mem_new_i64(cpu_env,
        offsetof(CPUARMState, exclusive_high), "exclusive_high");
}

/*
 * Return the core mmu_idx to use for A64 "unprivileged load/store" insns
 */
static int get_a64_user_mem_index(DisasContext *s)
{
    /*
     * If AccType_UNPRIV is not used, the insn uses AccType_NORMAL,
     * which is the usual mmu_idx for this cpu state.
     */
    ARMMMUIdx useridx = s->mmu_idx;

    if (s->unpriv) {
        /*
         * We have pre-computed the condition for AccType_UNPRIV.
         * Therefore we should never get here with a mmu_idx for
         * which we do not know the corresponding user mmu_idx.
         */
        switch (useridx) {
        case ARMMMUIdx_E10_1:
        case ARMMMUIdx_E10_1_PAN:
            useridx = ARMMMUIdx_E10_0;
            break;
        case ARMMMUIdx_E20_2:
        case ARMMMUIdx_E20_2_PAN:
            useridx = ARMMMUIdx_E20_0;
            break;
        case ARMMMUIdx_SE10_1:
        case ARMMMUIdx_SE10_1_PAN:
            useridx = ARMMMUIdx_SE10_0;
            break;
        case ARMMMUIdx_SE20_2:
        case ARMMMUIdx_SE20_2_PAN:
            useridx = ARMMMUIdx_SE20_0;
            break;
        default:
            g_assert_not_reached();
        }
    }
    return arm_to_core_mmu_idx(useridx);
}

static void reset_btype(DisasContext *s)
{
    if (s->btype != 0) {
        TCGv_i32 zero = tcg_const_i32(0);
        tcg_gen_st_i32(zero, cpu_env, offsetof(CPUARMState, btype));
        tcg_temp_free_i32(zero);
        s->btype = 0;
    }
}

static void set_btype(DisasContext *s, int val)
{
    TCGv_i32 tcg_val;

    /* BTYPE is a 2-bit field, and 0 should be done with reset_btype.  */
    tcg_debug_assert(val >= 1 && val <= 3);

    tcg_val = tcg_const_i32(val);
    tcg_gen_st_i32(tcg_val, cpu_env, offsetof(CPUARMState, btype));
    tcg_temp_free_i32(tcg_val);
    s->btype = -1;
}

void gen_a64_set_pc_im(uint64_t val)
{
    tcg_gen_movi_i64(cpu_pc, val);
}

/*
 * Handle Top Byte Ignore (TBI) bits.
 *
 * If address tagging is enabled via the TCR TBI bits:
 *  + for EL2 and EL3 there is only one TBI bit, and if it is set
 *    then the address is zero-extended, clearing bits [63:56]
 *  + for EL0 and EL1, TBI0 controls addresses with bit 55 == 0
 *    and TBI1 controls addressses with bit 55 == 1.
 *    If the appropriate TBI bit is set for the address then
 *    the address is sign-extended from bit 55 into bits [63:56]
 *
 * Here We have concatenated TBI{1,0} into tbi.
 */
static void gen_top_byte_ignore(DisasContext *s, TCGv_i64 dst,
                                TCGv_i64 src, int tbi)
{
    if (tbi == 0) {
        /* Load unmodified address */
        tcg_gen_mov_i64(dst, src);
    } else if (!regime_has_2_ranges(s->mmu_idx)) {
        /* Force tag byte to all zero */
        tcg_gen_extract_i64(dst, src, 0, 56);
    } else {
        /* Sign-extend from bit 55.  */
        tcg_gen_sextract_i64(dst, src, 0, 56);

        switch (tbi) {
        case 1:
            /* tbi0 but !tbi1: only use the extension if positive */
            tcg_gen_and_i64(dst, dst, src);
            break;
        case 2:
            /* !tbi0 but tbi1: only use the extension if negative */
            tcg_gen_or_i64(dst, dst, src);
            break;
        case 3:
            /* tbi0 and tbi1: always use the extension */
            break;
        default:
            g_assert_not_reached();
        }
    }
}

static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src)
{
    /*
     * If address tagging is enabled for instructions via the TCR TBI bits,
     * then loading an address into the PC will clear out any tag.
     */
    gen_top_byte_ignore(s, cpu_pc, src, s->tbii);
}

/*
 * Handle MTE and/or TBI.
 *
 * For TBI, ideally, we would do nothing.  Proper behaviour on fault is
 * for the tag to be present in the FAR_ELx register.  But for user-only
 * mode we do not have a TLB with which to implement this, so we must
 * remove the top byte now.
 *
 * Always return a fresh temporary that we can increment independently
 * of the write-back address.
 */

TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr)
{
    TCGv_i64 clean = new_tmp_a64(s);
#ifdef CONFIG_USER_ONLY
    gen_top_byte_ignore(s, clean, addr, s->tbid);
#else
    tcg_gen_mov_i64(clean, addr);
#endif
    return clean;
}

/* Insert a zero tag into src, with the result at dst. */
static void gen_address_with_allocation_tag0(TCGv_i64 dst, TCGv_i64 src)
{
    tcg_gen_andi_i64(dst, src, ~MAKE_64BIT_MASK(56, 4));
}

static void gen_probe_access(DisasContext *s, TCGv_i64 ptr,
                             MMUAccessType acc, int log2_size)
{
    TCGv_i32 t_acc = tcg_const_i32(acc);
    TCGv_i32 t_idx = tcg_const_i32(get_mem_index(s));
    TCGv_i32 t_size = tcg_const_i32(1 << log2_size);

    gen_helper_probe_access(cpu_env, ptr, t_acc, t_idx, t_size);
    tcg_temp_free_i32(t_acc);
    tcg_temp_free_i32(t_idx);
    tcg_temp_free_i32(t_size);
}

/*
 * For MTE, check a single logical or atomic access.  This probes a single
 * address, the exact one specified.  The size and alignment of the access
 * is not relevant to MTE, per se, but watchpoints do require the size,
 * and we want to recognize those before making any other changes to state.
 */
static TCGv_i64 gen_mte_check1_mmuidx(DisasContext *s, TCGv_i64 addr,
                                      bool is_write, bool tag_checked,
                                      int log2_size, bool is_unpriv,
                                      int core_idx)
{
    if (tag_checked && s->mte_active[is_unpriv]) {
        TCGv_i32 tcg_desc;
        TCGv_i64 ret;
        int desc = 0;

        desc = FIELD_DP32(desc, MTEDESC, MIDX, core_idx);
        desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
        desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
        desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write);
        desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << log2_size) - 1);
        tcg_desc = tcg_const_i32(desc);

        ret = new_tmp_a64(s);
        gen_helper_mte_check(ret, cpu_env, tcg_desc, addr);
        tcg_temp_free_i32(tcg_desc);

        return ret;
    }
    return clean_data_tbi(s, addr);
}

TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write,
                        bool tag_checked, int log2_size)
{
    return gen_mte_check1_mmuidx(s, addr, is_write, tag_checked, log2_size,
                                 false, get_mem_index(s));
}

/*
 * For MTE, check multiple logical sequential accesses.
 */
TCGv_i64 gen_mte_checkN(DisasContext *s, TCGv_i64 addr, bool is_write,
                        bool tag_checked, int size)
{
    if (tag_checked && s->mte_active[0]) {
        TCGv_i32 tcg_desc;
        TCGv_i64 ret;
        int desc = 0;

        desc = FIELD_DP32(desc, MTEDESC, MIDX, get_mem_index(s));
        desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
        desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
        desc = FIELD_DP32(desc, MTEDESC, WRITE, is_write);
        desc = FIELD_DP32(desc, MTEDESC, SIZEM1, size - 1);
        tcg_desc = tcg_const_i32(desc);

        ret = new_tmp_a64(s);
        gen_helper_mte_check(ret, cpu_env, tcg_desc, addr);
        tcg_temp_free_i32(tcg_desc);

        return ret;
    }
    return clean_data_tbi(s, addr);
}

typedef struct DisasCompare64 {
    TCGCond cond;
    TCGv_i64 value;
} DisasCompare64;

static void a64_test_cc(DisasCompare64 *c64, int cc)
{
    DisasCompare c32;

    arm_test_cc(&c32, cc);

    /* Sign-extend the 32-bit value so that the GE/LT comparisons work
       * properly.  The NE/EQ comparisons are also fine with this choice.  */
    c64->cond = c32.cond;
    c64->value = tcg_temp_new_i64();
    tcg_gen_ext_i32_i64(c64->value, c32.value);

    arm_free_cc(&c32);
}

static void a64_free_cc(DisasCompare64 *c64)
{
    tcg_temp_free_i64(c64->value);
}

static void gen_exception_internal(int excp)
{
    TCGv_i32 tcg_excp = tcg_const_i32(excp);

    assert(excp_is_internal(excp));
    gen_helper_exception_internal(cpu_env, tcg_excp);
    tcg_temp_free_i32(tcg_excp);
}

static void gen_exception_internal_insn(DisasContext *s, uint64_t pc, int excp)
{
    gen_a64_set_pc_im(pc);
    gen_exception_internal(excp);
    s->base.is_jmp = DISAS_NORETURN;
}

static void gen_exception_bkpt_insn(DisasContext *s, uint32_t syndrome)
{
    TCGv_i32 tcg_syn;

    gen_a64_set_pc_im(s->pc_curr);
    tcg_syn = tcg_const_i32(syndrome);
    gen_helper_exception_bkpt_insn(cpu_env, tcg_syn);
    tcg_temp_free_i32(tcg_syn);
    s->base.is_jmp = DISAS_NORETURN;
}

static void gen_step_complete_exception(DisasContext *s)
{
    /* We just completed step of an insn. Move from Active-not-pending
     * to Active-pending, and then also take the swstep exception.
     * This corresponds to making the (IMPDEF) choice to prioritize
     * swstep exceptions over asynchronous exceptions taken to an exception
     * level where debug is disabled. This choice has the advantage that
     * we do not need to maintain internal state corresponding to the
     * ISV/EX syndrome bits between completion of the step and generation
     * of the exception, and our syndrome information is always correct.
     */
    gen_ss_advance(s);
    gen_swstep_exception(s, 1, s->is_ldex);
    s->base.is_jmp = DISAS_NORETURN;
}

static inline bool use_goto_tb(DisasContext *s, uint64_t dest)
{
    if (s->ss_active) {
        return false;
    }
    return translator_use_goto_tb(&s->base, dest);
}

static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest)
{
    if (use_goto_tb(s, dest)) {
        tcg_gen_goto_tb(n);
        gen_a64_set_pc_im(dest);
        tcg_gen_exit_tb(s->base.tb, n);
        s->base.is_jmp = DISAS_NORETURN;
    } else {
        gen_a64_set_pc_im(dest);
        if (s->ss_active) {
            gen_step_complete_exception(s);
        } else {
            tcg_gen_lookup_and_goto_ptr();
            s->base.is_jmp = DISAS_NORETURN;
        }
    }
}

static void init_tmp_a64_array(DisasContext *s)
{
#ifdef CONFIG_DEBUG_TCG
    memset(s->tmp_a64, 0, sizeof(s->tmp_a64));
#endif
    s->tmp_a64_count = 0;
}

static void free_tmp_a64(DisasContext *s)
{
    int i;
    for (i = 0; i < s->tmp_a64_count; i++) {
        tcg_temp_free_i64(s->tmp_a64[i]);
    }
    init_tmp_a64_array(s);
}

TCGv_i64 new_tmp_a64(DisasContext *s)
{
    assert(s->tmp_a64_count < TMP_A64_MAX);
    return s->tmp_a64[s->tmp_a64_count++] = tcg_temp_new_i64();
}

TCGv_i64 new_tmp_a64_local(DisasContext *s)
{
    assert(s->tmp_a64_count < TMP_A64_MAX);
    return s->tmp_a64[s->tmp_a64_count++] = tcg_temp_local_new_i64();
}

TCGv_i64 new_tmp_a64_zero(DisasContext *s)
{
    TCGv_i64 t = new_tmp_a64(s);
    tcg_gen_movi_i64(t, 0);
    return t;
}

/*
 * Register access functions
 *
 * These functions are used for directly accessing a register in where
 * changes to the final register value are likely to be made. If you
 * need to use a register for temporary calculation (e.g. index type
 * operations) use the read_* form.
 *
 * B1.2.1 Register mappings
 *
 * In instruction register encoding 31 can refer to ZR (zero register) or
 * the SP (stack pointer) depending on context. In QEMU's case we map SP
 * to cpu_X[31] and ZR accesses to a temporary which can be discarded.
 * This is the point of the _sp forms.
 */
TCGv_i64 cpu_reg(DisasContext *s, int reg)
{
    if (reg == 31) {
        return new_tmp_a64_zero(s);
    } else {
        return cpu_X[reg];
    }
}

/* register access for when 31 == SP */
TCGv_i64 cpu_reg_sp(DisasContext *s, int reg)
{
    return cpu_X[reg];
}

/* read a cpu register in 32bit/64bit mode. Returns a TCGv_i64
 * representing the register contents. This TCGv is an auto-freed
 * temporary so it need not be explicitly freed, and may be modified.
 */
TCGv_i64 read_cpu_reg(DisasContext *s, int reg, int sf)
{
    TCGv_i64 v = new_tmp_a64(s);
    if (reg != 31) {
        if (sf) {
            tcg_gen_mov_i64(v, cpu_X[reg]);
        } else {
            tcg_gen_ext32u_i64(v, cpu_X[reg]);
        }
    } else {
        tcg_gen_movi_i64(v, 0);
    }
    return v;
}

TCGv_i64 read_cpu_reg_sp(DisasContext *s, int reg, int sf)
{
    TCGv_i64 v = new_tmp_a64(s);
    if (sf) {
        tcg_gen_mov_i64(v, cpu_X[reg]);
    } else {
        tcg_gen_ext32u_i64(v, cpu_X[reg]);
    }
    return v;
}

/* Return the offset into CPUARMState of a slice (from
 * the least significant end) of FP register Qn (ie
 * Dn, Sn, Hn or Bn).
 * (Note that this is not the same mapping as for A32; see cpu.h)
 */
static inline int fp_reg_offset(DisasContext *s, int regno, MemOp size)
{
    return vec_reg_offset(s, regno, 0, size);
}

/* Offset of the high half of the 128 bit vector Qn */
static inline int fp_reg_hi_offset(DisasContext *s, int regno)
{
    return vec_reg_offset(s, regno, 1, MO_64);
}

/* Convenience accessors for reading and writing single and double
 * FP registers. Writing clears the upper parts of the associated
 * 128 bit vector register, as required by the architecture.
 * Note that unlike the GP register accessors, the values returned
 * by the read functions must be manually freed.
 */
static TCGv_i64 read_fp_dreg(DisasContext *s, int reg)
{
    TCGv_i64 v = tcg_temp_new_i64();

    tcg_gen_ld_i64(v, cpu_env, fp_reg_offset(s, reg, MO_64));
    return v;
}

static TCGv_i32 read_fp_sreg(DisasContext *s, int reg)
{
    TCGv_i32 v = tcg_temp_new_i32();

    tcg_gen_ld_i32(v, cpu_env, fp_reg_offset(s, reg, MO_32));
    return v;
}

static TCGv_i32 read_fp_hreg(DisasContext *s, int reg)
{
    TCGv_i32 v = tcg_temp_new_i32();

    tcg_gen_ld16u_i32(v, cpu_env, fp_reg_offset(s, reg, MO_16));
    return v;
}

/* Clear the bits above an N-bit vector, for N = (is_q ? 128 : 64).
 * If SVE is not enabled, then there are only 128 bits in the vector.
 */
static void clear_vec_high(DisasContext *s, bool is_q, int rd)
{
    unsigned ofs = fp_reg_offset(s, rd, MO_64);
    unsigned vsz = vec_full_reg_size(s);

    /* Nop move, with side effect of clearing the tail. */
    tcg_gen_gvec_mov(MO_64, ofs, ofs, is_q ? 16 : 8, vsz);
}

void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v)
{
    unsigned ofs = fp_reg_offset(s, reg, MO_64);

    tcg_gen_st_i64(v, cpu_env, ofs);
    clear_vec_high(s, false, reg);
}

static void write_fp_sreg(DisasContext *s, int reg, TCGv_i32 v)
{
    TCGv_i64 tmp = tcg_temp_new_i64();

    tcg_gen_extu_i32_i64(tmp, v);
    write_fp_dreg(s, reg, tmp);
    tcg_temp_free_i64(tmp);
}

/* Expand a 2-operand AdvSIMD vector operation using an expander function.  */
static void gen_gvec_fn2(DisasContext *s, bool is_q, int rd, int rn,
                         GVecGen2Fn *gvec_fn, int vece)
{
    gvec_fn(vece, vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn),
            is_q ? 16 : 8, vec_full_reg_size(s));
}

/* Expand a 2-operand + immediate AdvSIMD vector operation using
 * an expander function.
 */
static void gen_gvec_fn2i(DisasContext *s, bool is_q, int rd, int rn,
                          int64_t imm, GVecGen2iFn *gvec_fn, int vece)
{
    gvec_fn(vece, vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn),
            imm, is_q ? 16 : 8, vec_full_reg_size(s));
}

/* Expand a 3-operand AdvSIMD vector operation using an expander function.  */
static void gen_gvec_fn3(DisasContext *s, bool is_q, int rd, int rn, int rm,
                         GVecGen3Fn *gvec_fn, int vece)
{
    gvec_fn(vece, vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn),
            vec_full_reg_offset(s, rm), is_q ? 16 : 8, vec_full_reg_size(s));
}

/* Expand a 4-operand AdvSIMD vector operation using an expander function.  */
static void gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm,
                         int rx, GVecGen4Fn *gvec_fn, int vece)
{
    gvec_fn(vece, vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn),
            vec_full_reg_offset(s, rm), vec_full_reg_offset(s, rx),
            is_q ? 16 : 8, vec_full_reg_size(s));
}

/* Expand a 2-operand operation using an out-of-line helper.  */
static void gen_gvec_op2_ool(DisasContext *s, bool is_q, int rd,
                             int rn, int data, gen_helper_gvec_2 *fn)
{
    tcg_gen_gvec_2_ool(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
}

/* Expand a 3-operand operation using an out-of-line helper.  */
static void gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd,
                             int rn, int rm, int data, gen_helper_gvec_3 *fn)
{
    tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       vec_full_reg_offset(s, rm),
                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
}

/* Expand a 3-operand + fpstatus pointer + simd data value operation using
 * an out-of-line helper.
 */
static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn,
                              int rm, bool is_fp16, int data,
                              gen_helper_gvec_3_ptr *fn)
{
    TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR);
    tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       vec_full_reg_offset(s, rm), fpst,
                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
    tcg_temp_free_ptr(fpst);
}

/* Expand a 3-operand + qc + operation using an out-of-line helper.  */
static void gen_gvec_op3_qc(DisasContext *s, bool is_q, int rd, int rn,
                            int rm, gen_helper_gvec_3_ptr *fn)
{
    TCGv_ptr qc_ptr = tcg_temp_new_ptr();

    tcg_gen_addi_ptr(qc_ptr, cpu_env, offsetof(CPUARMState, vfp.qc));
    tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       vec_full_reg_offset(s, rm), qc_ptr,
                       is_q ? 16 : 8, vec_full_reg_size(s), 0, fn);
    tcg_temp_free_ptr(qc_ptr);
}

/* Expand a 4-operand operation using an out-of-line helper.  */
static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
                             int rm, int ra, int data, gen_helper_gvec_4 *fn)
{
    tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       vec_full_reg_offset(s, rm),
                       vec_full_reg_offset(s, ra),
                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
}

/*
 * Expand a 4-operand + fpstatus pointer + simd data value operation using
 * an out-of-line helper.
 */
static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn,
                              int rm, int ra, bool is_fp16, int data,
                              gen_helper_gvec_4_ptr *fn)
{
    TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR);
    tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd),
                       vec_full_reg_offset(s, rn),
                       vec_full_reg_offset(s, rm),
                       vec_full_reg_offset(s, ra), fpst,
                       is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
    tcg_temp_free_ptr(fpst);
}

/* Set ZF and NF based on a 64 bit result. This is alas fiddlier
 * than the 32 bit equivalent.
 */
static inline void gen_set_NZ64(TCGv_i64 result)
{
    tcg_gen_extr_i64_i32(cpu_ZF, cpu_NF, result);
    tcg_gen_or_i32(cpu_ZF, cpu_ZF, cpu_NF);
}

/* Set NZCV as for a logical operation: NZ as per result, CV cleared. */
static inline void gen_logic_CC(int sf, TCGv_i64 result)
{
    if (sf) {
        gen_set_NZ64(result);
    } else {
        tcg_gen_extrl_i64_i32(cpu_ZF, result);
        tcg_gen_mov_i32(cpu_NF, cpu_ZF);
    }
    tcg_gen_movi_i32(cpu_CF, 0);
    tcg_gen_movi_i32(cpu_VF, 0);
}

/* dest = T0 + T1; compute C, N, V and Z flags */
static void gen_add_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        TCGv_i64 result, flag, tmp;
        result = tcg_temp_new_i64();
        flag = tcg_temp_new_i64();
        tmp = tcg_temp_new_i64();

        tcg_gen_movi_i64(tmp, 0);
        tcg_gen_add2_i64(result, flag, t0, tmp, t1, tmp);

        tcg_gen_extrl_i64_i32(cpu_CF, flag);

        gen_set_NZ64(result);

        tcg_gen_xor_i64(flag, result, t0);
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_andc_i64(flag, flag, tmp);
        tcg_temp_free_i64(tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, flag);

        tcg_gen_mov_i64(dest, result);
        tcg_temp_free_i64(result);
        tcg_temp_free_i64(flag);
    } else {
        /* 32 bit arithmetic */
        TCGv_i32 t0_32 = tcg_temp_new_i32();
        TCGv_i32 t1_32 = tcg_temp_new_i32();
        TCGv_i32 tmp = tcg_temp_new_i32();

        tcg_gen_movi_i32(tmp, 0);
        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, t0_32, tmp, t1_32, tmp);
        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);

        tcg_temp_free_i32(tmp);
        tcg_temp_free_i32(t0_32);
        tcg_temp_free_i32(t1_32);
    }
}

/* dest = T0 - T1; compute C, N, V and Z flags */
static void gen_sub_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        /* 64 bit arithmetic */
        TCGv_i64 result, flag, tmp;

        result = tcg_temp_new_i64();
        flag = tcg_temp_new_i64();
        tcg_gen_sub_i64(result, t0, t1);

        gen_set_NZ64(result);

        tcg_gen_setcond_i64(TCG_COND_GEU, flag, t0, t1);
        tcg_gen_extrl_i64_i32(cpu_CF, flag);

        tcg_gen_xor_i64(flag, result, t0);
        tmp = tcg_temp_new_i64();
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_and_i64(flag, flag, tmp);
        tcg_temp_free_i64(tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, flag);
        tcg_gen_mov_i64(dest, result);
        tcg_temp_free_i64(flag);
        tcg_temp_free_i64(result);
    } else {
        /* 32 bit arithmetic */
        TCGv_i32 t0_32 = tcg_temp_new_i32();
        TCGv_i32 t1_32 = tcg_temp_new_i32();
        TCGv_i32 tmp;

        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_sub_i32(cpu_NF, t0_32, t1_32);
        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_setcond_i32(TCG_COND_GEU, cpu_CF, t0_32, t1_32);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tmp = tcg_temp_new_i32();
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_temp_free_i32(t0_32);
        tcg_temp_free_i32(t1_32);
        tcg_gen_and_i32(cpu_VF, cpu_VF, tmp);
        tcg_temp_free_i32(tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);
    }
}

/* dest = T0 + T1 + CF; do not compute flags. */
static void gen_adc(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    TCGv_i64 flag = tcg_temp_new_i64();
    tcg_gen_extu_i32_i64(flag, cpu_CF);
    tcg_gen_add_i64(dest, t0, t1);
    tcg_gen_add_i64(dest, dest, flag);
    tcg_temp_free_i64(flag);

    if (!sf) {
        tcg_gen_ext32u_i64(dest, dest);
    }
}

/* dest = T0 + T1 + CF; compute C, N, V and Z flags. */
static void gen_adc_CC(int sf, TCGv_i64 dest, TCGv_i64 t0, TCGv_i64 t1)
{
    if (sf) {
        TCGv_i64 result, cf_64, vf_64, tmp;
        result = tcg_temp_new_i64();
        cf_64 = tcg_temp_new_i64();
        vf_64 = tcg_temp_new_i64();
        tmp = tcg_const_i64(0);

        tcg_gen_extu_i32_i64(cf_64, cpu_CF);
        tcg_gen_add2_i64(result, cf_64, t0, tmp, cf_64, tmp);
        tcg_gen_add2_i64(result, cf_64, result, cf_64, t1, tmp);
        tcg_gen_extrl_i64_i32(cpu_CF, cf_64);
        gen_set_NZ64(result);

        tcg_gen_xor_i64(vf_64, result, t0);
        tcg_gen_xor_i64(tmp, t0, t1);
        tcg_gen_andc_i64(vf_64, vf_64, tmp);
        tcg_gen_extrh_i64_i32(cpu_VF, vf_64);

        tcg_gen_mov_i64(dest, result);

        tcg_temp_free_i64(tmp);
        tcg_temp_free_i64(vf_64);
        tcg_temp_free_i64(cf_64);
        tcg_temp_free_i64(result);
    } else {
        TCGv_i32 t0_32, t1_32, tmp;
        t0_32 = tcg_temp_new_i32();
        t1_32 = tcg_temp_new_i32();
        tmp = tcg_const_i32(0);

        tcg_gen_extrl_i64_i32(t0_32, t0);
        tcg_gen_extrl_i64_i32(t1_32, t1);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, t0_32, tmp, cpu_CF, tmp);
        tcg_gen_add2_i32(cpu_NF, cpu_CF, cpu_NF, cpu_CF, t1_32, tmp);

        tcg_gen_mov_i32(cpu_ZF, cpu_NF);
        tcg_gen_xor_i32(cpu_VF, cpu_NF, t0_32);
        tcg_gen_xor_i32(tmp, t0_32, t1_32);
        tcg_gen_andc_i32(cpu_VF, cpu_VF, tmp);
        tcg_gen_extu_i32_i64(dest, cpu_NF);

        tcg_temp_free_i32(tmp);
        tcg_temp_free_i32(t1_32);
        tcg_temp_free_i32(t0_32);
    }
}

/*
 * Load/Store generators
 */

/*
 * Store from GPR register to memory.
 */
static void do_gpr_st_memidx(DisasContext *s, TCGv_i64 source,
                             TCGv_i64 tcg_addr, MemOp memop, int memidx,
                             bool iss_valid,
                             unsigned int iss_srt,
                             bool iss_sf, bool iss_ar)
{
    memop = finalize_memop(s, memop);
    tcg_gen_qemu_st_i64(source, tcg_addr, memidx, memop);

    if (iss_valid) {
        uint32_t syn;

        syn = syn_data_abort_with_iss(0,
                                      (memop & MO_SIZE),
                                      false,
                                      iss_srt,
                                      iss_sf,
                                      iss_ar,
                                      0, 0, 0, 0, 0, false);
        disas_set_insn_syndrome(s, syn);
    }
}

static void do_gpr_st(DisasContext *s, TCGv_i64 source,
                      TCGv_i64 tcg_addr, MemOp memop,
                      bool iss_valid,
                      unsigned int iss_srt,
                      bool iss_sf, bool iss_ar)
{
    do_gpr_st_memidx(s, source, tcg_addr, memop, get_mem_index(s),
                     iss_valid, iss_srt, iss_sf, iss_ar);
}

/*
 * Load from memory to GPR register
 */
static void do_gpr_ld_memidx(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
                             MemOp memop, bool extend, int memidx,
                             bool iss_valid, unsigned int iss_srt,
                             bool iss_sf, bool iss_ar)
{
    memop = finalize_memop(s, memop);
    tcg_gen_qemu_ld_i64(dest, tcg_addr, memidx, memop);

    if (extend && (memop & MO_SIGN)) {
        g_assert((memop & MO_SIZE) <= MO_32);
        tcg_gen_ext32u_i64(dest, dest);
    }

    if (iss_valid) {
        uint32_t syn;

        syn = syn_data_abort_with_iss(0,
                                      (memop & MO_SIZE),
                                      (memop & MO_SIGN) != 0,
                                      iss_srt,
                                      iss_sf,
                                      iss_ar,
                                      0, 0, 0, 0, 0, false);
        disas_set_insn_syndrome(s, syn);
    }
}

static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
                      MemOp memop, bool extend,
                      bool iss_valid, unsigned int iss_srt,
                      bool iss_sf, bool iss_ar)
{
    do_gpr_ld_memidx(s, dest, tcg_addr, memop, extend, get_mem_index(s),
                     iss_valid, iss_srt, iss_sf, iss_ar);
}

/*
 * Store from FP register to memory
 */
static void do_fp_st(DisasContext *s, int srcidx, TCGv_i64 tcg_addr, int size)
{
    /* This writes the bottom N bits of a 128 bit wide vector to memory */
    TCGv_i64 tmplo = tcg_temp_new_i64();
    MemOp mop;

    tcg_gen_ld_i64(tmplo, cpu_env, fp_reg_offset(s, srcidx, MO_64));

    if (size < 4) {
        mop = finalize_memop(s, size);
        tcg_gen_qemu_st_i64(tmplo, tcg_addr, get_mem_index(s), mop);
    } else {
        bool be = s->be_data == MO_BE;
        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
        TCGv_i64 tmphi = tcg_temp_new_i64();

        tcg_gen_ld_i64(tmphi, cpu_env, fp_reg_hi_offset(s, srcidx));

        mop = s->be_data | MO_Q;
        tcg_gen_qemu_st_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_st_i64(be ? tmplo : tmphi, tcg_hiaddr,
                            get_mem_index(s), mop);

        tcg_temp_free_i64(tcg_hiaddr);
        tcg_temp_free_i64(tmphi);
    }

    tcg_temp_free_i64(tmplo);
}

/*
 * Load from memory to FP register
 */
static void do_fp_ld(DisasContext *s, int destidx, TCGv_i64 tcg_addr, int size)
{
    /* This always zero-extends and writes to a full 128 bit wide vector */
    TCGv_i64 tmplo = tcg_temp_new_i64();
    TCGv_i64 tmphi = NULL;
    MemOp mop;

    if (size < 4) {

        mop = finalize_memop(s, size);
        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), mop);
    } else {
        bool be = s->be_data == MO_BE;
        TCGv_i64 tcg_hiaddr;

        tmphi = tcg_temp_new_i64();
        tcg_hiaddr = tcg_temp_new_i64();

        mop = s->be_data | MO_Q;
        tcg_gen_qemu_ld_i64(be ? tmphi : tmplo, tcg_addr, get_mem_index(s),
                            mop | (s->align_mem ? MO_ALIGN_16 : 0));
        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_ld_i64(be ? tmplo : tmphi, tcg_hiaddr,
                            get_mem_index(s), mop);
        tcg_temp_free_i64(tcg_hiaddr);
    }

    tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(s, destidx, MO_64));
    tcg_temp_free_i64(tmplo);

    if (tmphi) {
        tcg_gen_st_i64(tmphi, cpu_env, fp_reg_hi_offset(s, destidx));
        tcg_temp_free_i64(tmphi);
    }
    clear_vec_high(s, tmphi != NULL, destidx);
}

/*
 * Vector load/store helpers.
 *
 * The principal difference between this and a FP load is that we don't
 * zero extend as we are filling a partial chunk of the vector register.
 * These functions don't support 128 bit loads/stores, which would be
 * normal load/store operations.
 *
 * The _i32 versions are useful when operating on 32 bit quantities
 * (eg for floating point single or using Neon helper functions).
 */

/* Get value of an element within a vector register */
static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx,
                             int element, MemOp memop)
{
    int vect_off = vec_reg_offset(s, srcidx, element, memop & MO_SIZE);
    switch ((unsigned)memop) {
    case MO_8:
        tcg_gen_ld8u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_ld16u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_ld32u_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_8|MO_SIGN:
        tcg_gen_ld8s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16|MO_SIGN:
        tcg_gen_ld16s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32|MO_SIGN:
        tcg_gen_ld32s_i64(tcg_dest, cpu_env, vect_off);
        break;
    case MO_64:
    case MO_64|MO_SIGN:
        tcg_gen_ld_i64(tcg_dest, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

static void read_vec_element_i32(DisasContext *s, TCGv_i32 tcg_dest, int srcidx,
                                 int element, MemOp memop)
{
    int vect_off = vec_reg_offset(s, srcidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_ld8u_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_ld16u_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_8|MO_SIGN:
        tcg_gen_ld8s_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_16|MO_SIGN:
        tcg_gen_ld16s_i32(tcg_dest, cpu_env, vect_off);
        break;
    case MO_32:
    case MO_32|MO_SIGN:
        tcg_gen_ld_i32(tcg_dest, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

/* Set value of an element within a vector register */
static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
                              int element, MemOp memop)
{
    int vect_off = vec_reg_offset(s, destidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_st8_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_st16_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_st32_i64(tcg_src, cpu_env, vect_off);
        break;
    case MO_64:
        tcg_gen_st_i64(tcg_src, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src,
                                  int destidx, int element, MemOp memop)
{
    int vect_off = vec_reg_offset(s, destidx, element, memop & MO_SIZE);
    switch (memop) {
    case MO_8:
        tcg_gen_st8_i32(tcg_src, cpu_env, vect_off);
        break;
    case MO_16:
        tcg_gen_st16_i32(tcg_src, cpu_env, vect_off);
        break;
    case MO_32:
        tcg_gen_st_i32(tcg_src, cpu_env, vect_off);
        break;
    default:
        g_assert_not_reached();
    }
}

/* Store from vector register to memory */
static void do_vec_st(DisasContext *s, int srcidx, int element,
                      TCGv_i64 tcg_addr, MemOp mop)
{
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    read_vec_element(s, tcg_tmp, srcidx, element, mop & MO_SIZE);
    tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), mop);

    tcg_temp_free_i64(tcg_tmp);
}

/* Load from memory to vector register */
static void do_vec_ld(DisasContext *s, int destidx, int element,
                      TCGv_i64 tcg_addr, MemOp mop)
{
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), mop);
    write_vec_element(s, tcg_tmp, destidx, element, mop & MO_SIZE);

    tcg_temp_free_i64(tcg_tmp);
}

/* Check that FP/Neon access is enabled. If it is, return
 * true. If not, emit code to generate an appropriate exception,
 * and return false; the caller should not emit any code for
 * the instruction. Note that this check must happen after all
 * unallocated-encoding checks (otherwise the syndrome information
 * for the resulting exception will be incorrect).
 */
static bool fp_access_check(DisasContext *s)
{
    if (s->fp_excp_el) {
        assert(!s->fp_access_checked);
        s->fp_access_checked = true;

        gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
                           syn_fp_access_trap(1, 0xe, false), s->fp_excp_el);
        return false;
    }
    s->fp_access_checked = true;
    return true;
}

/* Check that SVE access is enabled.  If it is, return true.
 * If not, emit code to generate an appropriate exception and return false.
 */
bool sve_access_check(DisasContext *s)
{
    if (s->sve_excp_el) {
        assert(!s->sve_access_checked);
        s->sve_access_checked = true;

        gen_exception_insn(s, s->pc_curr, EXCP_UDEF,
                           syn_sve_access_trap(), s->sve_excp_el);
        return false;
    }
    s->sve_access_checked = true;
    return fp_access_check(s);
}

/*
 * This utility function is for doing register extension with an
 * optional shift. You will likely want to pass a temporary for the
 * destination register. See DecodeRegExtend() in the ARM ARM.
 */
static void ext_and_shift_reg(TCGv_i64 tcg_out, TCGv_i64 tcg_in,
                              int option, unsigned int shift)
{
    int extsize = extract32(option, 0, 2);
    bool is_signed = extract32(option, 2, 1);

    if (is_signed) {
        switch (extsize) {
        case 0:
            tcg_gen_ext8s_i64(tcg_out, tcg_in);
            break;
        case 1:
            tcg_gen_ext16s_i64(tcg_out, tcg_in);
            break;
        case 2:
            tcg_gen_ext32s_i64(tcg_out, tcg_in);
            break;
        case 3:
            tcg_gen_mov_i64(tcg_out, tcg_in);
            break;
        }
    } else {
        switch (extsize) {
        case 0:
            tcg_gen_ext8u_i64(tcg_out, tcg_in);
            break;
        case 1:
            tcg_gen_ext16u_i64(tcg_out, tcg_in);
            break;
        case 2:
            tcg_gen_ext32u_i64(tcg_out, tcg_in);
            break;
        case 3:
            tcg_gen_mov_i64(tcg_out, tcg_in);
            break;
        }
    }

    if (shift) {
        tcg_gen_shli_i64(tcg_out, tcg_out, shift);
    }
}

static inline void gen_check_sp_alignment(DisasContext *s)
{
    /* The AArch64 architecture mandates that (if enabled via PSTATE
     * or SCTLR bits) there is a check that SP is 16-aligned on every
     * SP-relative load or store (with an exception generated if it is not).
     * In line with general QEMU practice regarding misaligned accesses,
     * we omit these checks for the sake of guest program performance.
     * This function is provided as a hook so we can more easily add these
     * checks in future (possibly as a "favour catching guest program bugs
     * over speed" user selectable option).
     */
}

/*
 * This provides a simple table based table lookup decoder. It is
 * intended to be used when the relevant bits for decode are too
 * awkwardly placed and switch/if based logic would be confusing and
 * deeply nested. Since it's a linear search through the table, tables
 * should be kept small.
 *
 * It returns the first handler where insn & mask == pattern, or
 * NULL if there is no match.
 * The table is terminated by an empty mask (i.e. 0)
 */
static inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table,
                                               uint32_t insn)
{
    const AArch64DecodeTable *tptr = table;

    while (tptr->mask) {
        if ((insn & tptr->mask) == tptr->pattern) {
            return tptr->disas_fn;
        }
        tptr++;
    }
    return NULL;
}

/*
 * The instruction disassembly implemented here matches
 * the instruction encoding classifications in chapter C4
 * of the ARM Architecture Reference Manual (DDI0487B_a);
 * classification names and decode diagrams here should generally
 * match up with those in the manual.
 */

/* Unconditional branch (immediate)
 *   31  30       26 25                                  0
 * +----+-----------+-------------------------------------+
 * | op | 0 0 1 0 1 |                 imm26               |
 * +----+-----------+-------------------------------------+
 */
static void disas_uncond_b_imm(DisasContext *s, uint32_t insn)
{
    uint64_t addr = s->pc_curr + sextract32(insn, 0, 26) * 4;

    if (insn & (1U << 31)) {
        /* BL Branch with link */
        tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next);
    }

    /* B Branch / BL Branch with link */
    reset_btype(s);
    gen_goto_tb(s, 0, addr);
}

/* Compare and branch (immediate)
 *   31  30         25  24  23                  5 4      0
 * +----+-------------+----+---------------------+--------+
 * | sf | 0 1 1 0 1 0 | op |         imm19       |   Rt   |
 * +----+-------------+----+---------------------+--------+
 */
static void disas_comp_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int sf, op, rt;
    uint64_t addr;
    TCGLabel *label_match;
    TCGv_i64 tcg_cmp;

    sf = extract32(insn, 31, 1);
    op = extract32(insn, 24, 1); /* 0: CBZ; 1: CBNZ */
    rt = extract32(insn, 0, 5);
    addr = s->pc_curr + sextract32(insn, 5, 19) * 4;

    tcg_cmp = read_cpu_reg(s, rt, sf);
    label_match = gen_new_label();

    reset_btype(s);
    tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ,
                        tcg_cmp, 0, label_match);

    gen_goto_tb(s, 0, s->base.pc_next);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
}

/* Test and branch (immediate)
 *   31  30         25  24  23   19 18          5 4    0
 * +----+-------------+----+-------+-------------+------+
 * | b5 | 0 1 1 0 1 1 | op |  b40  |    imm14    |  Rt  |
 * +----+-------------+----+-------+-------------+------+
 */
static void disas_test_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int bit_pos, op, rt;
    uint64_t addr;
    TCGLabel *label_match;
    TCGv_i64 tcg_cmp;

    bit_pos = (extract32(insn, 31, 1) << 5) | extract32(insn, 19, 5);
    op = extract32(insn, 24, 1); /* 0: TBZ; 1: TBNZ */
    addr = s->pc_curr + sextract32(insn, 5, 14) * 4;
    rt = extract32(insn, 0, 5);

    tcg_cmp = tcg_temp_new_i64();
    tcg_gen_andi_i64(tcg_cmp, cpu_reg(s, rt), (1ULL << bit_pos));
    label_match = gen_new_label();

    reset_btype(s);
    tcg_gen_brcondi_i64(op ? TCG_COND_NE : TCG_COND_EQ,
                        tcg_cmp, 0, label_match);
    tcg_temp_free_i64(tcg_cmp);
    gen_goto_tb(s, 0, s->base.pc_next);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
}

/* Conditional branch (immediate)
 *  31           25  24  23                  5   4  3    0
 * +---------------+----+---------------------+----+------+
 * | 0 1 0 1 0 1 0 | o1 |         imm19       | o0 | cond |
 * +---------------+----+---------------------+----+------+
 */
static void disas_cond_b_imm(DisasContext *s, uint32_t insn)
{
    unsigned int cond;
    uint64_t addr;

    if ((insn & (1 << 4)) || (insn & (1 << 24))) {
        unallocated_encoding(s);
        return;
    }
    addr = s->pc_curr + sextract32(insn, 5, 19) * 4;
    cond = extract32(insn, 0, 4);

    reset_btype(s);
    if (cond < 0x0e) {
        /* genuinely conditional branches */
        TCGLabel *label_match = gen_new_label();
        arm_gen_test_cc(cond, label_match);
        gen_goto_tb(s, 0, s->base.pc_next);
        gen_set_label(label_match);
        gen_goto_tb(s, 1, addr);
    } else {
        /* 0xe and 0xf are both "always" conditions */
        gen_goto_tb(s, 0, addr);
    }
}

/* HINT instruction group, including various allocated HINTs */
static void handle_hint(DisasContext *s, uint32_t insn,
                        unsigned int op1, unsigned int op2, unsigned int crm)
{
    unsigned int selector = crm << 3 | op2;

    if (op1 != 3) {
        unallocated_encoding(s);
        return;
    }

    switch (selector) {
    case 0b00000: /* NOP */
        break;
    case 0b00011: /* WFI */
        s->base.is_jmp = DISAS_WFI;
        break;
    case 0b00001: /* YIELD */
        /* When running in MTTCG we don't generate jumps to the yield and
         * WFE helpers as it won't affect the scheduling of other vCPUs.
         * If we wanted to more completely model WFE/SEV so we don't busy
         * spin unnecessarily we would need to do something more involved.
         */
        if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) {
            s->base.is_jmp = DISAS_YIELD;
        }
        break;
    case 0b00010: /* WFE */
        if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) {
            s->base.is_jmp = DISAS_WFE;
        }
        break;
    case 0b00100: /* SEV */
    case 0b00101: /* SEVL */
        /* we treat all as NOP at least for now */
        break;
    case 0b00111: /* XPACLRI */
        if (s->pauth_active) {
            gen_helper_xpaci(cpu_X[30], cpu_env, cpu_X[30]);
        }
        break;
    case 0b01000: /* PACIA1716 */
        if (s->pauth_active) {
            gen_helper_pacia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]);
        }
        break;
    case 0b01010: /* PACIB1716 */
        if (s->pauth_active) {
            gen_helper_pacib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]);
        }
        break;
    case 0b01100: /* AUTIA1716 */
        if (s->pauth_active) {
            gen_helper_autia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]);
        }
        break;
    case 0b01110: /* AUTIB1716 */
        if (s->pauth_active) {
            gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]);
        }
        break;
    case 0b11000: /* PACIAZ */
        if (s->pauth_active) {
            gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30],
                                new_tmp_a64_zero(s));
        }
        break;
    case 0b11001: /* PACIASP */
        if (s->pauth_active) {
            gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]);
        }
        break;
    case 0b11010: /* PACIBZ */
        if (s->pauth_active) {
            gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30],
                                new_tmp_a64_zero(s));
        }
        break;
    case 0b11011: /* PACIBSP */
        if (s->pauth_active) {
            gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]);
        }
        break;
    case 0b11100: /* AUTIAZ */
        if (s->pauth_active) {
            gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30],
                              new_tmp_a64_zero(s));
        }
        break;
    case 0b11101: /* AUTIASP */
        if (s->pauth_active) {
            gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]);
        }
        break;
    case 0b11110: /* AUTIBZ */
        if (s->pauth_active) {
            gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30],
                              new_tmp_a64_zero(s));
        }
        break;
    case 0b11111: /* AUTIBSP */
        if (s->pauth_active) {
            gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]);
        }
        break;
    default:
        /* default specified as NOP equivalent */
        break;
    }
}

static void gen_clrex(DisasContext *s, uint32_t insn)
{
    tcg_gen_movi_i64(cpu_exclusive_addr, -1);
}

/* CLREX, DSB, DMB, ISB */
static void handle_sync(DisasContext *s, uint32_t insn,
                        unsigned int op1, unsigned int op2, unsigned int crm)
{
    TCGBar bar;

    if (op1 != 3) {
        unallocated_encoding(s);
        return;
    }

    switch (op2) {
    case 2: /* CLREX */
        gen_clrex(s, insn);
        return;
    case 4: /* DSB */
    case 5: /* DMB */
        switch (crm & 3) {
        case 1: /* MBReqTypes_Reads */
            bar = TCG_BAR_SC | TCG_MO_LD_LD | TCG_MO_LD_ST;
            break;
        case 2: /* MBReqTypes_Writes */
            bar = TCG_BAR_SC | TCG_MO_ST_ST;
            break;
        default: /* MBReqTypes_All */
            bar = TCG_BAR_SC | TCG_MO_ALL;
            break;
        }
        tcg_gen_mb(bar);
        return;
    case 6: /* ISB */
        /* We need to break the TB after this insn to execute
         * a self-modified code correctly and also to take
         * any pending interrupts immediately.
         */
        reset_btype(s);
        gen_goto_tb(s, 0, s->base.pc_next);
        return;

    case 7: /* SB */
        if (crm != 0 || !dc_isar_feature(aa64_sb, s)) {
            goto do_unallocated;
        }
        /*
         * TODO: There is no speculation barrier opcode for TCG;
         * MB and end the TB instead.
         */
        tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC);
        gen_goto_tb(s, 0, s->base.pc_next);
        return;

    default:
    do_unallocated:
        unallocated_encoding(s);
        return;
    }
}

static void gen_xaflag(void)
{
    TCGv_i32 z = tcg_temp_new_i32();

    tcg_gen_setcondi_i32(TCG_COND_EQ, z, cpu_ZF, 0);

    /*
     * (!C & !Z) << 31
     * (!(C | Z)) << 31
     * ~((C | Z) << 31)
     * ~-(C | Z)
     * (C | Z) - 1
     */
    tcg_gen_or_i32(cpu_NF, cpu_CF, z);
    tcg_gen_subi_i32(cpu_NF, cpu_NF, 1);

    /* !(Z & C) */
    tcg_gen_and_i32(cpu_ZF, z, cpu_CF);
    tcg_gen_xori_i32(cpu_ZF, cpu_ZF, 1);

    /* (!C & Z) << 31 -> -(Z & ~C) */
    tcg_gen_andc_i32(cpu_VF, z, cpu_CF);
    tcg_gen_neg_i32(cpu_VF, cpu_VF);

    /* C | Z */
    tcg_gen_or_i32(cpu_CF, cpu_CF, z);

    tcg_temp_free_i32(z);
}

static void gen_axflag(void)
{
    tcg_gen_sari_i32(cpu_VF, cpu_VF, 31);         /* V ? -1 : 0 */
    tcg_gen_andc_i32(cpu_CF, cpu_CF, cpu_VF);     /* C & !V */

    /* !(Z | V) -> !(!ZF | V) -> ZF & !V -> ZF & ~VF */
    tcg_gen_andc_i32(cpu_ZF, cpu_ZF, cpu_VF);

    tcg_gen_movi_i32(cpu_NF, 0);
    tcg_gen_movi_i32(cpu_VF, 0);
}

/* MSR (immediate) - move immediate to processor state field */
static void handle_msr_i(DisasContext *s, uint32_t insn,
                         unsigned int op1, unsigned int op2, unsigned int crm)
{
    TCGv_i32 t1;
    int op = op1 << 3 | op2;

    /* End the TB by default, chaining is ok.  */
    s->base.is_jmp = DISAS_TOO_MANY;

    switch (op) {
    case 0x00: /* CFINV */
        if (crm != 0 || !dc_isar_feature(aa64_condm_4, s)) {
            goto do_unallocated;
        }
        tcg_gen_xori_i32(cpu_CF, cpu_CF, 1);
        s->base.is_jmp = DISAS_NEXT;
        break;

    case 0x01: /* XAFlag */
        if (crm != 0 || !dc_isar_feature(aa64_condm_5, s)) {
            goto do_unallocated;
        }
        gen_xaflag();
        s->base.is_jmp = DISAS_NEXT;
        break;

    case 0x02: /* AXFlag */
        if (crm != 0 || !dc_isar_feature(aa64_condm_5, s)) {
            goto do_unallocated;
        }
        gen_axflag();
        s->base.is_jmp = DISAS_NEXT;
        break;

    case 0x03: /* UAO */
        if (!dc_isar_feature(aa64_uao, s) || s->current_el == 0) {
            goto do_unallocated;
        }
        if (crm & 1) {
            set_pstate_bits(PSTATE_UAO);
        } else {
            clear_pstate_bits(PSTATE_UAO);
        }
        t1 = tcg_const_i32(s->current_el);
        gen_helper_rebuild_hflags_a64(cpu_env, t1);
        tcg_temp_free_i32(t1);
        break;

    case 0x04: /* PAN */
        if (!dc_isar_feature(aa64_pan, s) || s->current_el == 0) {
            goto do_unallocated;
        }
        if (crm & 1) {
            set_pstate_bits(PSTATE_PAN);
        } else {
            clear_pstate_bits(PSTATE_PAN);
        }
        t1 = tcg_const_i32(s->current_el);
        gen_helper_rebuild_hflags_a64(cpu_env, t1);
        tcg_temp_free_i32(t1);
        break;

    case 0x05: /* SPSel */
        if (s->current_el == 0) {
            goto do_unallocated;
        }
        t1 = tcg_const_i32(crm & PSTATE_SP);
        gen_helper_msr_i_spsel(cpu_env, t1);
        tcg_temp_free_i32(t1);
        break;

    case 0x19: /* SSBS */
        if (!dc_isar_feature(aa64_ssbs, s)) {
            goto do_unallocated;
        }
        if (crm & 1) {
            set_pstate_bits(PSTATE_SSBS);
        } else {
            clear_pstate_bits(PSTATE_SSBS);
        }
        /* Don't need to rebuild hflags since SSBS is a nop */
        break;

    case 0x1a: /* DIT */
        if (!dc_isar_feature(aa64_dit, s)) {
            goto do_unallocated;
        }
        if (crm & 1) {
            set_pstate_bits(PSTATE_DIT);
        } else {
            clear_pstate_bits(PSTATE_DIT);
        }
        /* There's no need to rebuild hflags because DIT is a nop */
        break;

    case 0x1e: /* DAIFSet */
        t1 = tcg_const_i32(crm);
        gen_helper_msr_i_daifset(cpu_env, t1);
        tcg_temp_free_i32(t1);
        break;

    case 0x1f: /* DAIFClear */
        t1 = tcg_const_i32(crm);
        gen_helper_msr_i_daifclear(cpu_env, t1);
        tcg_temp_free_i32(t1);
        /* For DAIFClear, exit the cpu loop to re-evaluate pending IRQs.  */
        s->base.is_jmp = DISAS_UPDATE_EXIT;
        break;

    case 0x1c: /* TCO */
        if (dc_isar_feature(aa64_mte, s)) {
            /* Full MTE is enabled -- set the TCO bit as directed. */
            if (crm & 1) {
                set_pstate_bits(PSTATE_TCO);
            } else {
                clear_pstate_bits(PSTATE_TCO);
            }
            t1 = tcg_const_i32(s->current_el);
            gen_helper_rebuild_hflags_a64(cpu_env, t1);
            tcg_temp_free_i32(t1);
            /* Many factors, including TCO, go into MTE_ACTIVE. */
            s->base.is_jmp = DISAS_UPDATE_NOCHAIN;
        } else if (dc_isar_feature(aa64_mte_insn_reg, s)) {
            /* Only "instructions accessible at EL0" -- PSTATE.TCO is WI.  */
            s->base.is_jmp = DISAS_NEXT;
        } else {
            goto do_unallocated;
        }
        break;

    default:
    do_unallocated:
        unallocated_encoding(s);
        return;
    }
}

static void gen_get_nzcv(TCGv_i64 tcg_rt)
{
    TCGv_i32 tmp = tcg_temp_new_i32();
    TCGv_i32 nzcv = tcg_temp_new_i32();

    /* build bit 31, N */
    tcg_gen_andi_i32(nzcv, cpu_NF, (1U << 31));
    /* build bit 30, Z */
    tcg_gen_setcondi_i32(TCG_COND_EQ, tmp, cpu_ZF, 0);
    tcg_gen_deposit_i32(nzcv, nzcv, tmp, 30, 1);
    /* build bit 29, C */
    tcg_gen_deposit_i32(nzcv, nzcv, cpu_CF, 29, 1);
    /* build bit 28, V */
    tcg_gen_shri_i32(tmp, cpu_VF, 31);
    tcg_gen_deposit_i32(nzcv, nzcv, tmp, 28, 1);
    /* generate result */
    tcg_gen_extu_i32_i64(tcg_rt, nzcv);

    tcg_temp_free_i32(nzcv);
    tcg_temp_free_i32(tmp);
}

static void gen_set_nzcv(TCGv_i64 tcg_rt)
{
    TCGv_i32 nzcv = tcg_temp_new_i32();

    /* take NZCV from R[t] */
    tcg_gen_extrl_i64_i32(nzcv, tcg_rt);

    /* bit 31, N */
    tcg_gen_andi_i32(cpu_NF, nzcv, (1U << 31));
    /* bit 30, Z */
    tcg_gen_andi_i32(cpu_ZF, nzcv, (1 << 30));
    tcg_gen_setcondi_i32(TCG_COND_EQ, cpu_ZF, cpu_ZF, 0);
    /* bit 29, C */
    tcg_gen_andi_i32(cpu_CF, nzcv, (1 << 29));
    tcg_gen_shri_i32(cpu_CF, cpu_CF, 29);
    /* bit 28, V */
    tcg_gen_andi_i32(cpu_VF, nzcv, (1 << 28));
    tcg_gen_shli_i32(cpu_VF, cpu_VF, 3);
    tcg_temp_free_i32(nzcv);
}

/* MRS - move from system register
 * MSR (register) - move to system register
 * SYS
 * SYSL
 * These are all essentially the same insn in 'read' and 'write'
 * versions, with varying op0 fields.
 */
static void handle_sys(DisasContext *s, uint32_t insn, bool isread,
                       unsigned int op0, unsigned int op1, unsigned int op2,
                       unsigned int crn, unsigned int crm, unsigned int rt)
{
    const ARMCPRegInfo *ri;
    TCGv_i64 tcg_rt;

    ri = get_arm_cp_reginfo(s->cp_regs,
                            ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP,
                                               crn, crm, op0, op1, op2));

    if (!ri) {
        /* Unknown register; this might be a guest error or a QEMU
         * unimplemented feature.
         */
        qemu_log_mask(LOG_UNIMP, "%s access to unsupported AArch64 "
                      "system register op0:%d op1:%d crn:%d crm:%d op2:%d\n",
                      isread ? "read" : "write", op0, op1, crn, crm, op2);
        unallocated_encoding(s);
        return;
    }

    /* Check access permissions */
    if (!cp_access_ok(s->current_el, ri, isread)) {
        unallocated_encoding(s);
        return;
    }

    if (ri->accessfn) {
        /* Emit code to perform further access permissions checks at
         * runtime; this may result in an exception.
         */
        TCGv_ptr tmpptr;
        TCGv_i32 tcg_syn, tcg_isread;
        uint32_t syndrome;

        gen_a64_set_pc_im(s->pc_curr);
        tmpptr = tcg_const_ptr(ri);
        syndrome = syn_aa64_sysregtrap(op0, op1, op2, crn, crm, rt, isread);
        tcg_syn = tcg_const_i32(syndrome);
        tcg_isread = tcg_const_i32(isread);
        gen_helper_access_check_cp_reg(cpu_env, tmpptr, tcg_syn, tcg_isread);
        tcg_temp_free_ptr(tmpptr);
        tcg_temp_free_i32(tcg_syn);
        tcg_temp_free_i32(tcg_isread);
    } else if (ri->type & ARM_CP_RAISES_EXC) {
        /*
         * The readfn or writefn might raise an exception;
         * synchronize the CPU state in case it does.
         */
        gen_a64_set_pc_im(s->pc_curr);
    }

    /* Handle special cases first */
    switch (ri->type & ~(ARM_CP_FLAG_MASK & ~ARM_CP_SPECIAL)) {
    case ARM_CP_NOP:
        return;
    case ARM_CP_NZCV:
        tcg_rt = cpu_reg(s, rt);
        if (isread) {
            gen_get_nzcv(tcg_rt);
        } else {
            gen_set_nzcv(tcg_rt);
        }
        return;
    case ARM_CP_CURRENTEL:
        /* Reads as current EL value from pstate, which is
         * guaranteed to be constant by the tb flags.
         */
        tcg_rt = cpu_reg(s, rt);
        tcg_gen_movi_i64(tcg_rt, s->current_el << 2);
        return;
    case ARM_CP_DC_ZVA:
        /* Writes clear the aligned block of memory which rt points into. */
        if (s->mte_active[0]) {
            TCGv_i32 t_desc;
            int desc = 0;

            desc = FIELD_DP32(desc, MTEDESC, MIDX, get_mem_index(s));
            desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid);
            desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma);
            t_desc = tcg_const_i32(desc);

            tcg_rt = new_tmp_a64(s);
            gen_helper_mte_check_zva(tcg_rt, cpu_env, t_desc, cpu_reg(s, rt));
            tcg_temp_free_i32(t_desc);
        } else {
            tcg_rt = clean_data_tbi(s, cpu_reg(s, rt));
        }
        gen_helper_dc_zva(cpu_env, tcg_rt);
        return;
    case ARM_CP_DC_GVA:
        {
            TCGv_i64 clean_addr, tag;

            /*
             * DC_GVA, like DC_ZVA, requires that we supply the original
             * pointer for an invalid page.  Probe that address first.
             */
            tcg_rt = cpu_reg(s, rt);
            clean_addr = clean_data_tbi(s, tcg_rt);
            gen_probe_access(s, clean_addr, MMU_DATA_STORE, MO_8);

            if (s->ata) {
                /* Extract the tag from the register to match STZGM.  */
                tag = tcg_temp_new_i64();
                tcg_gen_shri_i64(tag, tcg_rt, 56);
                gen_helper_stzgm_tags(cpu_env, clean_addr, tag);
                tcg_temp_free_i64(tag);
            }
        }
        return;
    case ARM_CP_DC_GZVA:
        {
            TCGv_i64 clean_addr, tag;

            /* For DC_GZVA, we can rely on DC_ZVA for the proper fault. */
            tcg_rt = cpu_reg(s, rt);
            clean_addr = clean_data_tbi(s, tcg_rt);
            gen_helper_dc_zva(cpu_env, clean_addr);

            if (s->ata) {
                /* Extract the tag from the register to match STZGM.  */
                tag = tcg_temp_new_i64();
                tcg_gen_shri_i64(tag, tcg_rt, 56);
                gen_helper_stzgm_tags(cpu_env, clean_addr, tag);
                tcg_temp_free_i64(tag);
            }
        }
        return;
    default:
        break;
    }
    if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) {
        return;
    } else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) {
        return;
    }

    if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) {
        gen_io_start();
    }

    tcg_rt = cpu_reg(s, rt);

    if (isread) {
        if (ri->type & ARM_CP_CONST) {
            tcg_gen_movi_i64(tcg_rt, ri->resetvalue);
        } else if (ri->readfn) {
            TCGv_ptr tmpptr;
            tmpptr = tcg_const_ptr(ri);
            gen_helper_get_cp_reg64(tcg_rt, cpu_env, tmpptr);
            tcg_temp_free_ptr(tmpptr);
        } else {
            tcg_gen_ld_i64(tcg_rt, cpu_env, ri->fieldoffset);
        }
    } else {
        if (ri->type & ARM_CP_CONST) {
            /* If not forbidden by access permissions, treat as WI */
            return;
        } else if (ri->writefn) {
            TCGv_ptr tmpptr;
            tmpptr = tcg_const_ptr(ri);
            gen_helper_set_cp_reg64(cpu_env, tmpptr, tcg_rt);
            tcg_temp_free_ptr(tmpptr);
        } else {
            tcg_gen_st_i64(tcg_rt, cpu_env, ri->fieldoffset);
        }
    }

    if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) {
        /* I/O operations must end the TB here (whether read or write) */
        s->base.is_jmp = DISAS_UPDATE_EXIT;
    }
    if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) {
        /*
         * A write to any coprocessor regiser that ends a TB
         * must rebuild the hflags for the next TB.
         */
        TCGv_i32 tcg_el = tcg_const_i32(s->current_el);
        gen_helper_rebuild_hflags_a64(cpu_env, tcg_el);
        tcg_temp_free_i32(tcg_el);
        /*
         * We default to ending the TB on a coprocessor register write,
         * but allow this to be suppressed by the register definition
         * (usually only necessary to work around guest bugs).

         */
        s->base.is_jmp = DISAS_UPDATE_EXIT;
    }
}

/* System
 *  31                 22 21  20 19 18 16 15   12 11    8 7   5 4    0
 * +---------------------+---+-----+-----+-------+-------+-----+------+
 * | 1 1 0 1 0 1 0 1 0 0 | L | op0 | op1 |  CRn  |  CRm  | op2 |  Rt  |
 * +---------------------+---+-----+-----+-------+-------+-----+------+
 */
static void disas_system(DisasContext *s, uint32_t insn)
{
    unsigned int l, op0, op1, crn, crm, op2, rt;
    l = extract32(insn, 21, 1);
    op0 = extract32(insn, 19, 2);
    op1 = extract32(insn, 16, 3);
    crn = extract32(insn, 12, 4);
    crm = extract32(insn, 8, 4);
    op2 = extract32(insn, 5, 3);
    rt = extract32(insn, 0, 5);

    if (op0 == 0) {
        if (l || rt != 31) {
            unallocated_encoding(s);
            return;
        }
        switch (crn) {
        case 2: /* HINT (including allocated hints like NOP, YIELD, etc) */
            handle_hint(s, insn, op1, op2, crm);
            break;
        case 3: /* CLREX, DSB, DMB, ISB */
            handle_sync(s, insn, op1, op2, crm);
            break;
        case 4: /* MSR (immediate) */
            handle_msr_i(s, insn, op1, op2, crm);
            break;
        default:
            unallocated_encoding(s);
            break;
        }
        return;
    }
    handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt);
}

/* Exception generation
 *
 *  31             24 23 21 20                     5 4   2 1  0
 * +-----------------+-----+------------------------+-----+----+
 * | 1 1 0 1 0 1 0 0 | opc |          imm16         | op2 | LL |
 * +-----------------------+------------------------+----------+
 */
static void disas_exc(DisasContext *s, uint32_t insn)
{
    int opc = extract32(insn, 21, 3);
    int op2_ll = extract32(insn, 0, 5);
    int imm16 = extract32(insn, 5, 16);
    TCGv_i32 tmp;

    switch (opc) {
    case 0:
        /* For SVC, HVC and SMC we advance the single-step state
         * machine before taking the exception. This is architecturally
         * mandated, to ensure that single-stepping a system call
         * instruction works properly.
         */
        switch (op2_ll) {
        case 1:                                                     /* SVC */
            gen_ss_advance(s);
            gen_exception_insn(s, s->base.pc_next, EXCP_SWI,
                               syn_aa64_svc(imm16), default_exception_el(s));
            break;
        case 2:                                                     /* HVC */
            if (s->current_el == 0) {
                unallocated_encoding(s);
                break;
            }
            /* The pre HVC helper handles cases when HVC gets trapped
             * as an undefined insn by runtime configuration.
             */
            gen_a64_set_pc_im(s->pc_curr);
            gen_helper_pre_hvc(cpu_env);
            gen_ss_advance(s);
            gen_exception_insn(s, s->base.pc_next, EXCP_HVC,
                               syn_aa64_hvc(imm16), 2);
            break;
        case 3:                                                     /* SMC */
            if (s->current_el == 0) {
                unallocated_encoding(s);
                break;
            }
            gen_a64_set_pc_im(s->pc_curr);
            tmp = tcg_const_i32(syn_aa64_smc(imm16));
            gen_helper_pre_smc(cpu_env, tmp);
            tcg_temp_free_i32(tmp);
            gen_ss_advance(s);
            gen_exception_insn(s, s->base.pc_next, EXCP_SMC,
                               syn_aa64_smc(imm16), 3);
            break;
        default:
            unallocated_encoding(s);
            break;
        }
        break;
    case 1:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* BRK */
        gen_exception_bkpt_insn(s, syn_aa64_bkpt(imm16));
        break;
    case 2:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* HLT. This has two purposes.
         * Architecturally, it is an external halting debug instruction.
         * Since QEMU doesn't implement external debug, we treat this as
         * it is required for halting debug disabled: it will UNDEF.
         * Secondly, "HLT 0xf000" is the A64 semihosting syscall instruction.
         */
        if (semihosting_enabled() && imm16 == 0xf000) {
#ifndef CONFIG_USER_ONLY
            /* In system mode, don't allow userspace access to semihosting,
             * to provide some semblance of security (and for consistency
             * with our 32-bit semihosting).
             */
            if (s->current_el == 0) {
                unsupported_encoding(s, insn);
                break;
            }
#endif
            gen_exception_internal_insn(s, s->pc_curr, EXCP_SEMIHOST);
        } else {
            unsupported_encoding(s, insn);
        }
        break;
    case 5:
        if (op2_ll < 1 || op2_ll > 3) {
            unallocated_encoding(s);
            break;
        }
        /* DCPS1, DCPS2, DCPS3 */
        unsupported_encoding(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/* Unconditional branch (register)
 *  31           25 24   21 20   16 15   10 9    5 4     0
 * +---------------+-------+-------+-------+------+-------+
 * | 1 1 0 1 0 1 1 |  opc  |  op2  |  op3  |  Rn  |  op4  |
 * +---------------+-------+-------+-------+------+-------+
 */
static void disas_uncond_b_reg(DisasContext *s, uint32_t insn)
{
    unsigned int opc, op2, op3, rn, op4;
    unsigned btype_mod = 2;   /* 0: BR, 1: BLR, 2: other */
    TCGv_i64 dst;
    TCGv_i64 modifier;

    opc = extract32(insn, 21, 4);
    op2 = extract32(insn, 16, 5);
    op3 = extract32(insn, 10, 6);
    rn = extract32(insn, 5, 5);
    op4 = extract32(insn, 0, 5);

    if (op2 != 0x1f) {
        goto do_unallocated;
    }

    switch (opc) {
    case 0: /* BR */
    case 1: /* BLR */
    case 2: /* RET */
        btype_mod = opc;
        switch (op3) {
        case 0:
            /* BR, BLR, RET */
            if (op4 != 0) {
                goto do_unallocated;
            }
            dst = cpu_reg(s, rn);
            break;

        case 2:
        case 3:
            if (!dc_isar_feature(aa64_pauth, s)) {
                goto do_unallocated;
            }
            if (opc == 2) {
                /* RETAA, RETAB */
                if (rn != 0x1f || op4 != 0x1f) {
                    goto do_unallocated;
                }
                rn = 30;
                modifier = cpu_X[31];
            } else {
                /* BRAAZ, BRABZ, BLRAAZ, BLRABZ */
                if (op4 != 0x1f) {
                    goto do_unallocated;
                }
                modifier = new_tmp_a64_zero(s);
            }
            if (s->pauth_active) {
                dst = new_tmp_a64(s);
                if (op3 == 2) {
                    gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier);
                } else {
                    gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier);
                }
            } else {
                dst = cpu_reg(s, rn);
            }
            break;

        default:
            goto do_unallocated;
        }
        gen_a64_set_pc(s, dst);
        /* BLR also needs to load return address */
        if (opc == 1) {
            tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next);
        }
        break;

    case 8: /* BRAA */
    case 9: /* BLRAA */
        if (!dc_isar_feature(aa64_pauth, s)) {
            goto do_unallocated;
        }
        if ((op3 & ~1) != 2) {
            goto do_unallocated;
        }
        btype_mod = opc & 1;
        if (s->pauth_active) {
            dst = new_tmp_a64(s);
            modifier = cpu_reg_sp(s, op4);
            if (op3 == 2) {
                gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier);
            } else {
                gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier);
            }
        } else {
            dst = cpu_reg(s, rn);
        }
        gen_a64_set_pc(s, dst);
        /* BLRAA also needs to load return address */
        if (opc == 9) {
            tcg_gen_movi_i64(cpu_reg(s, 30), s->base.pc_next);
        }
        break;

    case 4: /* ERET */
        if (s->current_el == 0) {
            goto do_unallocated;
        }
        switch (op3) {
        case 0: /* ERET */
            if (op4 != 0) {
                goto do_unallocated;
            }
            dst = tcg_temp_new_i64();
            tcg_gen_ld_i64(dst, cpu_env,
                           offsetof(CPUARMState, elr_el[s->current_el]));
            break;

        case 2: /* ERETAA */
        case 3: /* ERETAB */
            if (!dc_isar_feature(aa64_pauth, s)) {
                goto do_unallocated;
            }
            if (rn != 0x1f || op4 != 0x1f) {
                goto do_unallocated;
            }
            dst = tcg_temp_new_i64();
            tcg_gen_ld_i64(dst, cpu_env,
                           offsetof(CPUARMState, elr_el[s->current_el]));
            if (s->pauth_active) {
                modifier = cpu_X[31];
                if (op3 == 2) {
                    gen_helper_autia(dst, cpu_env, dst, modifier);
                } else {
                    gen_helper_autib(dst, cpu_env, dst, modifier);
                }
            }
            break;

        default:
            goto do_unallocated;
        }
        if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) {
            gen_io_start();
        }

        gen_helper_exception_return(cpu_env, dst);
        tcg_temp_free_i64(dst);
        /* Must exit loop to check un-masked IRQs */
        s->base.is_jmp = DISAS_EXIT;
        return;

    case 5: /* DRPS */
        if (op3 != 0 || op4 != 0 || rn != 0x1f) {
            goto do_unallocated;
        } else {
            unsupported_encoding(s, insn);
        }
        return;

    default:
    do_unallocated:
        unallocated_encoding(s);
        return;
    }

    switch (btype_mod) {
    case 0: /* BR */
        if (dc_isar_feature(aa64_bti, s)) {
            /* BR to {x16,x17} or !guard -> 1, else 3.  */
            set_btype(s, rn == 16 || rn == 17 || !s->guarded_page ? 1 : 3);
        }
        break;

    case 1: /* BLR */
        if (dc_isar_feature(aa64_bti, s)) {
            /* BLR sets BTYPE to 2, regardless of source guarded page.  */
            set_btype(s, 2);
        }
        break;

    default: /* RET or none of the above.  */
        /* BTYPE will be set to 0 by normal end-of-insn processing.  */
        break;
    }

    s->base.is_jmp = DISAS_JUMP;
}

/* Branches, exception generating and system instructions */
static void disas_b_exc_sys(DisasContext *s, uint32_t insn)
{
    switch (extract32(insn, 25, 7)) {
    case 0x0a: case 0x0b:
    case 0x4a: case 0x4b: /* Unconditional branch (immediate) */
        disas_uncond_b_imm(s, insn);
        break;
    case 0x1a: case 0x5a: /* Compare & branch (immediate) */
        disas_comp_b_imm(s, insn);
        break;
    case 0x1b: case 0x5b: /* Test & branch (immediate) */
        disas_test_b_imm(s, insn);
        break;
    case 0x2a: /* Conditional branch (immediate) */
        disas_cond_b_imm(s, insn);
        break;
    case 0x6a: /* Exception generation / System */
        if (insn & (1 << 24)) {
            if (extract32(insn, 22, 2) == 0) {
                disas_system(s, insn);
            } else {
                unallocated_encoding(s);
            }
        } else {
            disas_exc(s, insn);
        }
        break;
    case 0x6b: /* Unconditional branch (register) */
        disas_uncond_b_reg(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

/*
 * Load/Store exclusive instructions are implemented by remembering
 * the value/address loaded, and seeing if these are the same
 * when the store is performed. This is not actually the architecturally
 * mandated semantics, but it works for typical guest code sequences
 * and avoids having to monitor regular stores.
 *
 * The store exclusive uses the atomic cmpxchg primitives to avoid
 * races in multi-threaded linux-user and when MTTCG softmmu is
 * enabled.
 */
static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                               TCGv_i64 addr, int size, bool is_pair)
{
    int idx = get_mem_index(s);
    MemOp memop = s->be_data;

    g_assert(size <= 3);
    if (is_pair) {
        g_assert(size >= 2);
        if (size == 2) {
            /* The pair must be single-copy atomic for the doubleword.  */
            memop |= MO_64 | MO_ALIGN;
            tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
            if (s->be_data == MO_LE) {
                tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 0, 32);
                tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 32, 32);
            } else {
                tcg_gen_extract_i64(cpu_reg(s, rt), cpu_exclusive_val, 32, 32);
                tcg_gen_extract_i64(cpu_reg(s, rt2), cpu_exclusive_val, 0, 32);
            }
        } else {
            /* The pair must be single-copy atomic for *each* doubleword, not
               the entire quadword, however it must be quadword aligned.  */
            memop |= MO_64;
            tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx,
                                memop | MO_ALIGN_16);

            TCGv_i64 addr2 = tcg_temp_new_i64();
            tcg_gen_addi_i64(addr2, addr, 8);
            tcg_gen_qemu_ld_i64(cpu_exclusive_high, addr2, idx, memop);
            tcg_temp_free_i64(addr2);

            tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val);
            tcg_gen_mov_i64(cpu_reg(s, rt2), cpu_exclusive_high);
        }
    } else {
        memop |= size | MO_ALIGN;
        tcg_gen_qemu_ld_i64(cpu_exclusive_val, addr, idx, memop);
        tcg_gen_mov_i64(cpu_reg(s, rt), cpu_exclusive_val);
    }
    tcg_gen_mov_i64(cpu_exclusive_addr, addr);
}

static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
                                TCGv_i64 addr, int size, int is_pair)
{
    /* if (env->exclusive_addr == addr && env->exclusive_val == [addr]
     *     && (!is_pair || env->exclusive_high == [addr + datasize])) {
     *     [addr] = {Rt};
     *     if (is_pair) {
     *         [addr + datasize] = {Rt2};
     *     }
     *     {Rd} = 0;
     * } else {
     *     {Rd} = 1;
     * }
     * env->exclusive_addr = -1;
     */
    TCGLabel *fail_label = gen_new_label();
    TCGLabel *done_label = gen_new_label();
    TCGv_i64 tmp;

    tcg_gen_brcond_i64(TCG_COND_NE, addr, cpu_exclusive_addr, fail_label);

    tmp = tcg_temp_new_i64();
    if (is_pair) {
        if (size == 2) {
            if (s->be_data == MO_LE) {
                tcg_gen_concat32_i64(tmp, cpu_reg(s, rt), cpu_reg(s, rt2));
            } else {
                tcg_gen_concat32_i64(tmp, cpu_reg(s, rt2), cpu_reg(s, rt));
            }
            tcg_gen_atomic_cmpxchg_i64(tmp, cpu_exclusive_addr,
                                       cpu_exclusive_val, tmp,
                                       get_mem_index(s),
                                       MO_64 | MO_ALIGN | s->be_data);
            tcg_gen_setcond_i64(TCG_COND_NE, tmp, tmp, cpu_exclusive_val);
        } else if (tb_cflags(s->base.tb) & CF_PARALLEL) {
            if (!HAVE_CMPXCHG128) {
                gen_helper_exit_atomic(cpu_env);
                s->base.is_jmp = DISAS_NORETURN;
            } else if (s->be_data == MO_LE) {
                gen_helper_paired_cmpxchg64_le_parallel(tmp, cpu_env,
                                                        cpu_exclusive_addr,
                                                        cpu_reg(s, rt),
                                                        cpu_reg(s, rt2));
            } else {
                gen_helper_paired_cmpxchg64_be_parallel(tmp, cpu_env,
                                                        cpu_exclusive_addr,
                                                        cpu_reg(s, rt),
                                                        cpu_reg(s, rt2));
            }
        } else if (s->be_data == MO_LE) {
            gen_helper_paired_cmpxchg64_le(tmp, cpu_env, cpu_exclusive_addr,
                                           cpu_reg(s, rt), cpu_reg(s, rt2));
        } else {
            gen_helper_paired_cmpxchg64_be(tmp, cpu_env, cpu_exclusive_addr,
                                           cpu_reg(s, rt), cpu_reg(s, rt2));
        }
    } else {
        tcg_gen_atomic_cmpxchg_i64(tmp, cpu_exclusive_addr, cpu_exclusive_val,
                                   cpu_reg(s, rt), get_mem_index(s),
                                   size | MO_ALIGN | s->be_data);
        tcg_gen_setcond_i64(TCG_COND_NE, tmp, tmp, cpu_exclusive_val);
    }
    tcg_gen_mov_i64(cpu_reg(s, rd), tmp);
    tcg_temp_free_i64(tmp);
    tcg_gen_br(done_label);

    gen_set_label(fail_label);
    tcg_gen_movi_i64(cpu_reg(s, rd), 1);
    gen_set_label(done_label);
    tcg_gen_movi_i64(cpu_exclusive_addr, -1);
}

static void gen_compare_and_swap(DisasContext *s, int rs, int rt,
                                 int rn, int size)
{
    TCGv_i64 tcg_rs = cpu_reg(s, rs);
    TCGv_i64 tcg_rt = cpu_reg(s, rt);
    int memidx = get_mem_index(s);
    TCGv_i64 clean_addr;

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size);
    tcg_gen_atomic_cmpxchg_i64(tcg_rs, clean_addr, tcg_rs, tcg_rt, memidx,
                               size | MO_ALIGN | s->be_data);
}

static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt,
                                      int rn, int size)
{
    TCGv_i64 s1 = cpu_reg(s, rs);
    TCGv_i64 s2 = cpu_reg(s, rs + 1);
    TCGv_i64 t1 = cpu_reg(s, rt);
    TCGv_i64 t2 = cpu_reg(s, rt + 1);
    TCGv_i64 clean_addr;
    int memidx = get_mem_index(s);

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }

    /* This is a single atomic access, despite the "pair". */
    clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), true, rn != 31, size + 1);

    if (size == 2) {
        TCGv_i64 cmp = tcg_temp_new_i64();
        TCGv_i64 val = tcg_temp_new_i64();

        if (s->be_data == MO_LE) {
            tcg_gen_concat32_i64(val, t1, t2);
            tcg_gen_concat32_i64(cmp, s1, s2);
        } else {
            tcg_gen_concat32_i64(val, t2, t1);
            tcg_gen_concat32_i64(cmp, s2, s1);
        }

        tcg_gen_atomic_cmpxchg_i64(cmp, clean_addr, cmp, val, memidx,
                                   MO_64 | MO_ALIGN | s->be_data);
        tcg_temp_free_i64(val);

        if (s->be_data == MO_LE) {
            tcg_gen_extr32_i64(s1, s2, cmp);
        } else {
            tcg_gen_extr32_i64(s2, s1, cmp);
        }
        tcg_temp_free_i64(cmp);
    } else if (tb_cflags(s->base.tb) & CF_PARALLEL) {
        if (HAVE_CMPXCHG128) {
            TCGv_i32 tcg_rs = tcg_const_i32(rs);
            if (s->be_data == MO_LE) {
                gen_helper_casp_le_parallel(cpu_env, tcg_rs,
                                            clean_addr, t1, t2);
            } else {
                gen_helper_casp_be_parallel(cpu_env, tcg_rs,
                                            clean_addr, t1, t2);
            }
            tcg_temp_free_i32(tcg_rs);
        } else {
            gen_helper_exit_atomic(cpu_env);
            s->base.is_jmp = DISAS_NORETURN;
        }
    } else {
        TCGv_i64 d1 = tcg_temp_new_i64();
        TCGv_i64 d2 = tcg_temp_new_i64();
        TCGv_i64 a2 = tcg_temp_new_i64();
        TCGv_i64 c1 = tcg_temp_new_i64();
        TCGv_i64 c2 = tcg_temp_new_i64();
        TCGv_i64 zero = tcg_const_i64(0);

        /* Load the two words, in memory order.  */
        tcg_gen_qemu_ld_i64(d1, clean_addr, memidx,
                            MO_64 | MO_ALIGN_16 | s->be_data);
        tcg_gen_addi_i64(a2, clean_addr, 8);
        tcg_gen_qemu_ld_i64(d2, a2, memidx, MO_64 | s->be_data);

        /* Compare the two words, also in memory order.  */
        tcg_gen_setcond_i64(TCG_COND_EQ, c1, d1, s1);
        tcg_gen_setcond_i64(TCG_COND_EQ, c2, d2, s2);
        tcg_gen_and_i64(c2, c2, c1);

        /* If compare equal, write back new data, else write back old data.  */
        tcg_gen_movcond_i64(TCG_COND_NE, c1, c2, zero, t1, d1);
        tcg_gen_movcond_i64(TCG_COND_NE, c2, c2, zero, t2, d2);
        tcg_gen_qemu_st_i64(c1, clean_addr, memidx, MO_64 | s->be_data);
        tcg_gen_qemu_st_i64(c2, a2, memidx, MO_64 | s->be_data);
        tcg_temp_free_i64(a2);
        tcg_temp_free_i64(c1);
        tcg_temp_free_i64(c2);
        tcg_temp_free_i64(zero);

        /* Write back the data from memory to Rs.  */
        tcg_gen_mov_i64(s1, d1);
        tcg_gen_mov_i64(s2, d2);
        tcg_temp_free_i64(d1);
        tcg_temp_free_i64(d2);
    }
}

/* Update the Sixty-Four bit (SF) registersize. This logic is derived
 * from the ARMv8 specs for LDR (Shared decode for all encodings).
 */
static bool disas_ldst_compute_iss_sf(int size, bool is_signed, int opc)
{
    int opc0 = extract32(opc, 0, 1);
    int regsize;

    if (is_signed) {
        regsize = opc0 ? 32 : 64;
    } else {
        regsize = size == 3 ? 64 : 32;
    }
    return regsize == 64;
}

/* Load/store exclusive
 *
 *  31 30 29         24  23  22   21  20  16  15  14   10 9    5 4    0
 * +-----+-------------+----+---+----+------+----+-------+------+------+
 * | sz  | 0 0 1 0 0 0 | o2 | L | o1 |  Rs  | o0 |  Rt2  |  Rn  | Rt   |
 * +-----+-------------+----+---+----+------+----+-------+------+------+
 *
 *  sz: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64 bit
 *   L: 0 -> store, 1 -> load
 *  o2: 0 -> exclusive, 1 -> not
 *  o1: 0 -> single register, 1 -> register pair
 *  o0: 1 -> load-acquire/store-release, 0 -> not
 */
static void disas_ldst_excl(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    int rs = extract32(insn, 16, 5);
    int is_lasr = extract32(insn, 15, 1);
    int o2_L_o1_o0 = extract32(insn, 21, 3) * 2 | is_lasr;
    int size = extract32(insn, 30, 2);
    TCGv_i64 clean_addr;

    switch (o2_L_o1_o0) {
    case 0x0: /* STXR */
    case 0x1: /* STLXR */
        if (rn == 31) {
            gen_check_sp_alignment(s);
        }
        if (is_lasr) {
            tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
        }
        clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                    true, rn != 31, size);
        gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, false);
        return;

    case 0x4: /* LDXR */
    case 0x5: /* LDAXR */
        if (rn == 31) {
            gen_check_sp_alignment(s);
        }
        clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                    false, rn != 31, size);
        s->is_ldex = true;
        gen_load_exclusive(s, rt, rt2, clean_addr, size, false);
        if (is_lasr) {
            tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
        }
        return;

    case 0x8: /* STLLR */
        if (!dc_isar_feature(aa64_lor, s)) {
            break;
        }
        /* StoreLORelease is the same as Store-Release for QEMU.  */
        /* fall through */
    case 0x9: /* STLR */
        /* Generate ISS for non-exclusive accesses including LASR.  */
        if (rn == 31) {
            gen_check_sp_alignment(s);
        }
        tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
        clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                    true, rn != 31, size);
        /* TODO: ARMv8.4-LSE SCTLR.nAA */
        do_gpr_st(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, true, rt,
                  disas_ldst_compute_iss_sf(size, false, 0), is_lasr);
        return;

    case 0xc: /* LDLAR */
        if (!dc_isar_feature(aa64_lor, s)) {
            break;
        }
        /* LoadLOAcquire is the same as Load-Acquire for QEMU.  */
        /* fall through */
    case 0xd: /* LDAR */
        /* Generate ISS for non-exclusive accesses including LASR.  */
        if (rn == 31) {
            gen_check_sp_alignment(s);
        }
        clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                    false, rn != 31, size);
        /* TODO: ARMv8.4-LSE SCTLR.nAA */
        do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size | MO_ALIGN, false, true,
                  rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr);
        tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
        return;

    case 0x2: case 0x3: /* CASP / STXP */
        if (size & 2) { /* STXP / STLXP */
            if (rn == 31) {
                gen_check_sp_alignment(s);
            }
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL);
            }
            clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                        true, rn != 31, size);
            gen_store_exclusive(s, rs, rt, rt2, clean_addr, size, true);
            return;
        }
        if (rt2 == 31
            && ((rt | rs) & 1) == 0
            && dc_isar_feature(aa64_atomics, s)) {
            /* CASP / CASPL */
            gen_compare_and_swap_pair(s, rs, rt, rn, size | 2);
            return;
        }
        break;

    case 0x6: case 0x7: /* CASPA / LDXP */
        if (size & 2) { /* LDXP / LDAXP */
            if (rn == 31) {
                gen_check_sp_alignment(s);
            }
            clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn),
                                        false, rn != 31, size);
            s->is_ldex = true;
            gen_load_exclusive(s, rt, rt2, clean_addr, size, true);
            if (is_lasr) {
                tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ);
            }
            return;
        }
        if (rt2 == 31
            && ((rt | rs) & 1) == 0
            && dc_isar_feature(aa64_atomics, s)) {
            /* CASPA / CASPAL */
            gen_compare_and_swap_pair(s, rs, rt, rn, size | 2);
            return;
        }
        break;

    case 0xa: /* CAS */
    case 0xb: /* CASL */
    case 0xe: /* CASA */
    case 0xf: /* CASAL */
        if (rt2 == 31 && dc_isar_feature(aa64_atomics, s)) {
            gen_compare_and_swap(s, rs, rt, rn, size);
            return;
        }
        break;
    }
    unallocated_encoding(s);
}

/*
 * Load register (literal)
 *
 *  31 30 29   27  26 25 24 23                5 4     0
 * +-----+-------+---+-----+-------------------+-------+
 * | opc | 0 1 1 | V | 0 0 |     imm19         |  Rt   |
 * +-----+-------+---+-----+-------------------+-------+
 *
 * V: 1 -> vector (simd/fp)
 * opc (non-vector): 00 -> 32 bit, 01 -> 64 bit,
 *                   10-> 32 bit signed, 11 -> prefetch
 * opc (vector): 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit (11 unallocated)
 */
static void disas_ld_lit(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int64_t imm = sextract32(insn, 5, 19) << 2;
    bool is_vector = extract32(insn, 26, 1);
    int opc = extract32(insn, 30, 2);
    bool is_signed = false;
    int size = 2;
    TCGv_i64 tcg_rt, clean_addr;

    if (is_vector) {
        if (opc == 3) {
            unallocated_encoding(s);
            return;
        }
        size = 2 + opc;
        if (!fp_access_check(s)) {
            return;
        }
    } else {
        if (opc == 3) {
            /* PRFM (literal) : prefetch */
            return;
        }
        size = 2 + extract32(opc, 0, 1);
        is_signed = extract32(opc, 1, 1);
    }

    tcg_rt = cpu_reg(s, rt);

    clean_addr = tcg_const_i64(s->pc_curr + imm);
    if (is_vector) {
        do_fp_ld(s, rt, clean_addr, size);
    } else {
        /* Only unsigned 32bit loads target 32bit registers.  */
        bool iss_sf = opc != 0;

        do_gpr_ld(s, tcg_rt, clean_addr, size + is_signed * MO_SIGN,
                  false, true, rt, iss_sf, false);
    }
    tcg_temp_free_i64(clean_addr);
}

/*
 * LDNP (Load Pair - non-temporal hint)
 * LDP (Load Pair - non vector)
 * LDPSW (Load Pair Signed Word - non vector)
 * STNP (Store Pair - non-temporal hint)
 * STP (Store Pair - non vector)
 * LDNP (Load Pair of SIMD&FP - non-temporal hint)
 * LDP (Load Pair of SIMD&FP)
 * STNP (Store Pair of SIMD&FP - non-temporal hint)
 * STP (Store Pair of SIMD&FP)
 *
 *  31 30 29   27  26  25 24   23  22 21   15 14   10 9    5 4    0
 * +-----+-------+---+---+-------+---+-----------------------------+
 * | opc | 1 0 1 | V | 0 | index | L |  imm7 |  Rt2  |  Rn  | Rt   |
 * +-----+-------+---+---+-------+---+-------+-------+------+------+
 *
 * opc: LDP/STP/LDNP/STNP        00 -> 32 bit, 10 -> 64 bit
 *      LDPSW/STGP               01
 *      LDP/STP/LDNP/STNP (SIMD) 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit
 *   V: 0 -> GPR, 1 -> Vector
 * idx: 00 -> signed offset with non-temporal hint, 01 -> post-index,
 *      10 -> signed offset, 11 -> pre-index
 *   L: 0 -> Store 1 -> Load
 *
 * Rt, Rt2 = GPR or SIMD registers to be stored
 * Rn = general purpose register containing address
 * imm7 = signed offset (multiple of 4 or 8 depending on size)
 */
static void disas_ldst_pair(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    uint64_t offset = sextract64(insn, 15, 7);
    int index = extract32(insn, 23, 2);
    bool is_vector = extract32(insn, 26, 1);
    bool is_load = extract32(insn, 22, 1);
    int opc = extract32(insn, 30, 2);

    bool is_signed = false;
    bool postindex = false;
    bool wback = false;
    bool set_tag = false;

    TCGv_i64 clean_addr, dirty_addr;

    int size;

    if (opc == 3) {
        unallocated_encoding(s);
        return;
    }

    if (is_vector) {
        size = 2 + opc;
    } else if (opc == 1 && !is_load) {
        /* STGP */
        if (!dc_isar_feature(aa64_mte_insn_reg, s) || index == 0) {
            unallocated_encoding(s);
            return;
        }
        size = 3;
        set_tag = true;
    } else {
        size = 2 + extract32(opc, 1, 1);
        is_signed = extract32(opc, 0, 1);
        if (!is_load && is_signed) {
            unallocated_encoding(s);
            return;
        }
    }

    switch (index) {
    case 1: /* post-index */
        postindex = true;
        wback = true;
        break;
    case 0:
        /* signed offset with "non-temporal" hint. Since we don't emulate
         * caches we don't care about hints to the cache system about
         * data access patterns, and handle this identically to plain
         * signed offset.
         */
        if (is_signed) {
            /* There is no non-temporal-hint version of LDPSW */
            unallocated_encoding(s);
            return;
        }
        postindex = false;
        break;
    case 2: /* signed offset, rn not updated */
        postindex = false;
        break;
    case 3: /* pre-index */
        postindex = false;
        wback = true;
        break;
    }

    if (is_vector && !fp_access_check(s)) {
        return;
    }

    offset <<= (set_tag ? LOG2_TAG_GRANULE : size);

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }

    dirty_addr = read_cpu_reg_sp(s, rn, 1);
    if (!postindex) {
        tcg_gen_addi_i64(dirty_addr, dirty_addr, offset);
    }

    if (set_tag) {
        if (!s->ata) {
            /*
             * TODO: We could rely on the stores below, at least for
             * system mode, if we arrange to add MO_ALIGN_16.
             */
            gen_helper_stg_stub(cpu_env, dirty_addr);
        } else if (tb_cflags(s->base.tb) & CF_PARALLEL) {
            gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr);
        } else {
            gen_helper_stg(cpu_env, dirty_addr, dirty_addr);
        }
    }

    clean_addr = gen_mte_checkN(s, dirty_addr, !is_load,
                                (wback || rn != 31) && !set_tag, 2 << size);

    if (is_vector) {
        if (is_load) {
            do_fp_ld(s, rt, clean_addr, size);
        } else {
            do_fp_st(s, rt, clean_addr, size);
        }
        tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size);
        if (is_load) {
            do_fp_ld(s, rt2, clean_addr, size);
        } else {
            do_fp_st(s, rt2, clean_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        TCGv_i64 tcg_rt2 = cpu_reg(s, rt2);

        if (is_load) {
            TCGv_i64 tmp = tcg_temp_new_i64();

            /* Do not modify tcg_rt before recognizing any exception
             * from the second load.
             */
            do_gpr_ld(s, tmp, clean_addr, size + is_signed * MO_SIGN,
                      false, false, 0, false, false);
            tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size);
            do_gpr_ld(s, tcg_rt2, clean_addr, size + is_signed * MO_SIGN,
                      false, false, 0, false, false);

            tcg_gen_mov_i64(tcg_rt, tmp);
            tcg_temp_free_i64(tmp);
        } else {
            do_gpr_st(s, tcg_rt, clean_addr, size,
                      false, 0, false, false);
            tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size);
            do_gpr_st(s, tcg_rt2, clean_addr, size,