translate-a64.c 191 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
/*
 *  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 of the License, or (at your option) any later version.
 *
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
 */
#include <stdarg.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#include <inttypes.h>

#include "cpu.h"
#include "tcg-op.h"
#include "qemu/log.h"
#include "translate.h"
#include "qemu/host-utils.h"

31
32
#include "exec/gen-icount.h"

33
34
35
36
37
38
#include "helper.h"
#define GEN_HELPER 1
#include "helper.h"

static TCGv_i64 cpu_X[32];
static TCGv_i64 cpu_pc;
39
static TCGv_i32 cpu_NF, cpu_ZF, cpu_CF, cpu_VF;
40

41
42
43
44
45
46
47
48
49
/* Load/store exclusive handling */
static TCGv_i64 cpu_exclusive_addr;
static TCGv_i64 cpu_exclusive_val;
static TCGv_i64 cpu_exclusive_high;
#ifdef CONFIG_USER_ONLY
static TCGv_i64 cpu_exclusive_test;
static TCGv_i32 cpu_exclusive_info;
#endif

50
51
52
53
54
55
56
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"
};

57
58
59
60
61
62
63
enum a64_shift_type {
    A64_SHIFT_TYPE_LSL = 0,
    A64_SHIFT_TYPE_LSR = 1,
    A64_SHIFT_TYPE_ASR = 2,
    A64_SHIFT_TYPE_ROR = 3
};

64
65
66
67
68
69
70
71
72
73
74
/* 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;

75
76
77
78
79
80
81
82
83
84
85
86
87
88
/* initialize TCG globals.  */
void a64_translate_init(void)
{
    int i;

    cpu_pc = tcg_global_mem_new_i64(TCG_AREG0,
                                    offsetof(CPUARMState, pc),
                                    "pc");
    for (i = 0; i < 32; i++) {
        cpu_X[i] = tcg_global_mem_new_i64(TCG_AREG0,
                                          offsetof(CPUARMState, xregs[i]),
                                          regnames[i]);
    }

89
90
91
92
    cpu_NF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, NF), "NF");
    cpu_ZF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, ZF), "ZF");
    cpu_CF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, CF), "CF");
    cpu_VF = tcg_global_mem_new_i32(TCG_AREG0, offsetof(CPUARMState, VF), "VF");
93
94
95
96
97
98
99
100
101
102
103
104
105

    cpu_exclusive_addr = tcg_global_mem_new_i64(TCG_AREG0,
        offsetof(CPUARMState, exclusive_addr), "exclusive_addr");
    cpu_exclusive_val = tcg_global_mem_new_i64(TCG_AREG0,
        offsetof(CPUARMState, exclusive_val), "exclusive_val");
    cpu_exclusive_high = tcg_global_mem_new_i64(TCG_AREG0,
        offsetof(CPUARMState, exclusive_high), "exclusive_high");
#ifdef CONFIG_USER_ONLY
    cpu_exclusive_test = tcg_global_mem_new_i64(TCG_AREG0,
        offsetof(CPUARMState, exclusive_test), "exclusive_test");
    cpu_exclusive_info = tcg_global_mem_new_i32(TCG_AREG0,
        offsetof(CPUARMState, exclusive_info), "exclusive_info");
#endif
106
107
108
109
110
111
112
}

void aarch64_cpu_dump_state(CPUState *cs, FILE *f,
                            fprintf_function cpu_fprintf, int flags)
{
    ARMCPU *cpu = ARM_CPU(cs);
    CPUARMState *env = &cpu->env;
113
    uint32_t psr = pstate_read(env);
114
115
116
117
118
119
120
121
122
123
124
125
    int i;

    cpu_fprintf(f, "PC=%016"PRIx64"  SP=%016"PRIx64"\n",
            env->pc, env->xregs[31]);
    for (i = 0; i < 31; i++) {
        cpu_fprintf(f, "X%02d=%016"PRIx64, i, env->xregs[i]);
        if ((i % 4) == 3) {
            cpu_fprintf(f, "\n");
        } else {
            cpu_fprintf(f, " ");
        }
    }
126
127
128
129
130
131
    cpu_fprintf(f, "PSTATE=%08x (flags %c%c%c%c)\n",
                psr,
                psr & PSTATE_N ? 'N' : '-',
                psr & PSTATE_Z ? 'Z' : '-',
                psr & PSTATE_C ? 'C' : '-',
                psr & PSTATE_V ? 'V' : '-');
132
    cpu_fprintf(f, "\n");
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148

    if (flags & CPU_DUMP_FPU) {
        int numvfpregs = 32;
        for (i = 0; i < numvfpregs; i += 2) {
            uint64_t vlo = float64_val(env->vfp.regs[i * 2]);
            uint64_t vhi = float64_val(env->vfp.regs[(i * 2) + 1]);
            cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 " ",
                        i, vhi, vlo);
            vlo = float64_val(env->vfp.regs[(i + 1) * 2]);
            vhi = float64_val(env->vfp.regs[((i + 1) * 2) + 1]);
            cpu_fprintf(f, "q%02d=%016" PRIx64 ":%016" PRIx64 "\n",
                        i + 1, vhi, vlo);
        }
        cpu_fprintf(f, "FPCR: %08x  FPSR: %08x\n",
                    vfp_get_fpcr(env), vfp_get_fpsr(env));
    }
149
150
}

151
152
153
154
155
156
157
158
159
static int get_mem_index(DisasContext *s)
{
#ifdef CONFIG_USER_ONLY
    return 1;
#else
    return s->user;
#endif
}

160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
void gen_a64_set_pc_im(uint64_t val)
{
    tcg_gen_movi_i64(cpu_pc, val);
}

static void gen_exception(int excp)
{
    TCGv_i32 tmp = tcg_temp_new_i32();
    tcg_gen_movi_i32(tmp, excp);
    gen_helper_exception(cpu_env, tmp);
    tcg_temp_free_i32(tmp);
}

static void gen_exception_insn(DisasContext *s, int offset, int excp)
{
    gen_a64_set_pc_im(s->pc - offset);
    gen_exception(excp);
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
    s->is_jmp = DISAS_EXC;
}

static inline bool use_goto_tb(DisasContext *s, int n, uint64_t dest)
{
    /* No direct tb linking with singlestep or deterministic io */
    if (s->singlestep_enabled || (s->tb->cflags & CF_LAST_IO)) {
        return false;
    }

    /* Only link tbs from inside the same guest page */
    if ((s->tb->pc & TARGET_PAGE_MASK) != (dest & TARGET_PAGE_MASK)) {
        return false;
    }

    return true;
}

static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest)
{
    TranslationBlock *tb;

    tb = s->tb;
    if (use_goto_tb(s, n, dest)) {
        tcg_gen_goto_tb(n);
        gen_a64_set_pc_im(dest);
        tcg_gen_exit_tb((tcg_target_long)tb + n);
        s->is_jmp = DISAS_TB_JUMP;
    } else {
        gen_a64_set_pc_im(dest);
        if (s->singlestep_enabled) {
            gen_exception(EXCP_DEBUG);
        }
        tcg_gen_exit_tb(0);
        s->is_jmp = DISAS_JUMP;
    }
213
214
}

215
static void unallocated_encoding(DisasContext *s)
216
217
218
219
{
    gen_exception_insn(s, 4, EXCP_UDEF);
}

220
221
222
223
224
225
226
227
#define unsupported_encoding(s, insn)                                    \
    do {                                                                 \
        qemu_log_mask(LOG_UNIMP,                                         \
                      "%s:%d: unsupported instruction encoding 0x%08x "  \
                      "at pc=%016" PRIx64 "\n",                          \
                      __FILE__, __LINE__, insn, s->pc - 4);              \
        unallocated_encoding(s);                                         \
    } while (0);
228

229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
static void init_tmp_a64_array(DisasContext *s)
{
#ifdef CONFIG_DEBUG_TCG
    int i;
    for (i = 0; i < ARRAY_SIZE(s->tmp_a64); i++) {
        TCGV_UNUSED_I64(s->tmp_a64[i]);
    }
#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);
}

static 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();
}

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

262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
/*
 * 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.
 */
277
278
279
280
281
282
283
284
285
static TCGv_i64 cpu_reg(DisasContext *s, int reg)
{
    if (reg == 31) {
        return new_tmp_a64_zero(s);
    } else {
        return cpu_X[reg];
    }
}

286
287
288
289
290
291
/* register access for when 31 == SP */
static TCGv_i64 cpu_reg_sp(DisasContext *s, int reg)
{
    return cpu_X[reg];
}

292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
/* 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.
 */
static 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;
}

311
312
313
314
315
316
317
318
319
320
321
static 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;
}

322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
/* Return the offset into CPUARMState of an element of specified
 * size, 'element' places in from the least significant end of
 * the FP/vector register Qn.
 */
static inline int vec_reg_offset(int regno, int element, TCGMemOp size)
{
    int offs = offsetof(CPUARMState, vfp.regs[regno * 2]);
#ifdef HOST_WORDS_BIGENDIAN
    /* This is complicated slightly because vfp.regs[2n] is
     * still the low half and  vfp.regs[2n+1] the high half
     * of the 128 bit vector, even on big endian systems.
     * Calculate the offset assuming a fully bigendian 128 bits,
     * then XOR to account for the order of the two 64 bit halves.
     */
    offs += (16 - ((element + 1) * (1 << size)));
    offs ^= 8;
#else
    offs += element * (1 << size);
#endif
    return offs;
}

344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
/* 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(int regno, TCGMemOp size)
{
    int offs = offsetof(CPUARMState, vfp.regs[regno * 2]);
#ifdef HOST_WORDS_BIGENDIAN
    offs += (8 - (1 << size));
#endif
    return offs;
}

/* Offset of the high half of the 128 bit vector Qn */
static inline int fp_reg_hi_offset(int regno)
{
    return offsetof(CPUARMState, vfp.regs[regno * 2 + 1]);
}

364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
/* 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(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(reg, MO_32));
    return v;
}

static void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v)
{
    TCGv_i64 tcg_zero = tcg_const_i64(0);

    tcg_gen_st_i64(v, cpu_env, fp_reg_offset(reg, MO_64));
    tcg_gen_st_i64(tcg_zero, cpu_env, fp_reg_hi_offset(reg));
    tcg_temp_free_i64(tcg_zero);
}

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);
}

static TCGv_ptr get_fpstatus_ptr(void)
{
    TCGv_ptr statusptr = tcg_temp_new_ptr();
    int offset;

    /* In A64 all instructions (both FP and Neon) use the FPCR;
     * there is no equivalent of the A32 Neon "standard FPSCR value"
     * and all operations use vfp.fp_status.
     */
    offset = offsetof(CPUARMState, vfp.fp_status);
    tcg_gen_addi_ptr(statusptr, cpu_env, offset);
    return statusptr;
}

418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
/* 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)
{
    TCGv_i64 flag = tcg_temp_new_i64();

    tcg_gen_setcondi_i64(TCG_COND_NE, flag, result, 0);
    tcg_gen_trunc_i64_i32(cpu_ZF, flag);
    tcg_gen_shri_i64(flag, result, 32);
    tcg_gen_trunc_i64_i32(cpu_NF, flag);
    tcg_temp_free_i64(flag);
}

/* 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_trunc_i64_i32(cpu_ZF, result);
        tcg_gen_trunc_i64_i32(cpu_NF, result);
    }
    tcg_gen_movi_i32(cpu_CF, 0);
    tcg_gen_movi_i32(cpu_VF, 0);
}

445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
/* 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_trunc_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_shri_i64(flag, flag, 32);
        tcg_gen_trunc_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_trunc_i64_i32(t0_32, t0);
        tcg_gen_trunc_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_trunc_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_shri_i64(flag, flag, 32);
        tcg_gen_trunc_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_trunc_i64_i32(t0_32, t0);
        tcg_gen_trunc_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);
    }
}

541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
/* 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_trunc_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_shri_i64(vf_64, vf_64, 32);
        tcg_gen_trunc_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_trunc_i64_i32(t0_32, t0);
        tcg_gen_trunc_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);
    }
}

606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
/*
 * Load/Store generators
 */

/*
 * Store from GPR register to memory
 */
static void do_gpr_st(DisasContext *s, TCGv_i64 source,
                      TCGv_i64 tcg_addr, int size)
{
    g_assert(size <= 3);
    tcg_gen_qemu_st_i64(source, tcg_addr, get_mem_index(s), MO_TE + size);
}

/*
 * Load from memory to GPR register
 */
static void do_gpr_ld(DisasContext *s, TCGv_i64 dest, TCGv_i64 tcg_addr,
                      int size, bool is_signed, bool extend)
{
    TCGMemOp memop = MO_TE + size;

    g_assert(size <= 3);

    if (is_signed) {
        memop += MO_SIGN;
    }

    tcg_gen_qemu_ld_i64(dest, tcg_addr, get_mem_index(s), memop);

    if (extend && is_signed) {
        g_assert(size < 3);
        tcg_gen_ext32u_i64(dest, dest);
    }
}

/*
 * 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 tmp = tcg_temp_new_i64();
649
    tcg_gen_ld_i64(tmp, cpu_env, fp_reg_offset(srcidx, MO_64));
650
651
652
653
654
655
    if (size < 4) {
        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TE + size);
    } else {
        TCGv_i64 tcg_hiaddr = tcg_temp_new_i64();
        tcg_gen_qemu_st_i64(tmp, tcg_addr, get_mem_index(s), MO_TEQ);
        tcg_gen_qemu_st64(tmp, tcg_addr, get_mem_index(s));
656
        tcg_gen_ld_i64(tmp, cpu_env, fp_reg_hi_offset(srcidx));
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_st_i64(tmp, tcg_hiaddr, get_mem_index(s), MO_TEQ);
        tcg_temp_free_i64(tcg_hiaddr);
    }

    tcg_temp_free_i64(tmp);
}

/*
 * 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;

    if (size < 4) {
        TCGMemOp memop = MO_TE + size;
        tmphi = tcg_const_i64(0);
        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), memop);
    } else {
        TCGv_i64 tcg_hiaddr;
        tmphi = tcg_temp_new_i64();
        tcg_hiaddr = tcg_temp_new_i64();

        tcg_gen_qemu_ld_i64(tmplo, tcg_addr, get_mem_index(s), MO_TEQ);
        tcg_gen_addi_i64(tcg_hiaddr, tcg_addr, 8);
        tcg_gen_qemu_ld_i64(tmphi, tcg_hiaddr, get_mem_index(s), MO_TEQ);
        tcg_temp_free_i64(tcg_hiaddr);
    }

689
690
    tcg_gen_st_i64(tmplo, cpu_env, fp_reg_offset(destidx, MO_64));
    tcg_gen_st_i64(tmphi, cpu_env, fp_reg_hi_offset(destidx));
691
692
693
694
695

    tcg_temp_free_i64(tmplo);
    tcg_temp_free_i64(tmphi);
}

696
697
698
699
700
701
702
/*
 * 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.
703
704
705
 *
 * The _i32 versions are useful when operating on 32 bit quantities
 * (eg for floating point single or using Neon helper functions).
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
 */

/* Get value of an element within a vector register */
static void read_vec_element(DisasContext *s, TCGv_i64 tcg_dest, int srcidx,
                             int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(srcidx, element, memop & MO_SIZE);
    switch (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();
    }
}

741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
static void read_vec_element_i32(DisasContext *s, TCGv_i32 tcg_dest, int srcidx,
                                 int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(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();
    }
}

767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
/* Set value of an element within a vector register */
static void write_vec_element(DisasContext *s, TCGv_i64 tcg_src, int destidx,
                              int element, TCGMemOp memop)
{
    int vect_off = vec_reg_offset(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();
    }
}

/* Clear the high 64 bits of a 128 bit vector (in general non-quad
 * vector ops all need to do this).
 */
static void clear_vec_high(DisasContext *s, int rd)
{
    TCGv_i64 tcg_zero = tcg_const_i64(0);

    write_vec_element(s, tcg_zero, rd, 1, MO_64);
    tcg_temp_free_i64(tcg_zero);
}

/* Store from vector register to memory */
static void do_vec_st(DisasContext *s, int srcidx, int element,
                      TCGv_i64 tcg_addr, int size)
{
    TCGMemOp memop = MO_TE + size;
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    read_vec_element(s, tcg_tmp, srcidx, element, size);
    tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);

    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, int size)
{
    TCGMemOp memop = MO_TE + size;
    TCGv_i64 tcg_tmp = tcg_temp_new_i64();

    tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop);
    write_vec_element(s, tcg_tmp, destidx, element, size);

    tcg_temp_free_i64(tcg_tmp);
}

827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
/*
 * 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);
    }
}

875
876
877
878
879
880
881
882
883
884
885
886
887
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).
     */
}

888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
/*
 * 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;
}

913
914
915
916
917
918
/*
 * the instruction disassembly implemented here matches
 * the instruction encoding classifications in chapter 3 (C3)
 * of the ARM Architecture Reference Manual (DDI0487A_a)
 */

919
920
921
922
923
924
/* C3.2.7 Unconditional branch (immediate)
 *   31  30       26 25                                  0
 * +----+-----------+-------------------------------------+
 * | op | 0 0 1 0 1 |                 imm26               |
 * +----+-----------+-------------------------------------+
 */
925
926
static void disas_uncond_b_imm(DisasContext *s, uint32_t insn)
{
927
928
929
930
931
932
933
934
935
    uint64_t addr = s->pc + sextract32(insn, 0, 26) * 4 - 4;

    if (insn & (1 << 31)) {
        /* C5.6.26 BL Branch with link */
        tcg_gen_movi_i64(cpu_reg(s, 30), s->pc);
    }

    /* C5.6.20 B Branch / C5.6.26 BL Branch with link */
    gen_goto_tb(s, 0, addr);
936
937
}

938
939
940
941
942
943
/* C3.2.1 Compare & branch (immediate)
 *   31  30         25  24  23                  5 4      0
 * +----+-------------+----+---------------------+--------+
 * | sf | 0 1 1 0 1 0 | op |         imm19       |   Rt   |
 * +----+-------------+----+---------------------+--------+
 */
944
945
static void disas_comp_b_imm(DisasContext *s, uint32_t insn)
{
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
    unsigned int sf, op, rt;
    uint64_t addr;
    int 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 + sextract32(insn, 5, 19) * 4 - 4;

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

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

    gen_goto_tb(s, 0, s->pc);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
965
966
}

967
968
969
970
971
972
/* C3.2.5 Test & branch (immediate)
 *   31  30         25  24  23   19 18          5 4    0
 * +----+-------------+----+-------+-------------+------+
 * | b5 | 0 1 1 0 1 1 | op |  b40  |    imm14    |  Rt  |
 * +----+-------------+----+-------+-------------+------+
 */
973
974
static void disas_test_b_imm(DisasContext *s, uint32_t insn)
{
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
    unsigned int bit_pos, op, rt;
    uint64_t addr;
    int 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 + sextract32(insn, 5, 14) * 4 - 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();
    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->pc);
    gen_set_label(label_match);
    gen_goto_tb(s, 1, addr);
994
995
}

996
997
998
999
1000
1001
/* C3.2.2 / C5.6.19 Conditional branch (immediate)
 *  31           25  24  23                  5   4  3    0
 * +---------------+----+---------------------+----+------+
 * | 0 1 0 1 0 1 0 | o1 |         imm19       | o0 | cond |
 * +---------------+----+---------------------+----+------+
 */
1002
1003
static void disas_cond_b_imm(DisasContext *s, uint32_t insn)
{
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
    unsigned int cond;
    uint64_t addr;

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

    if (cond < 0x0e) {
        /* genuinely conditional branches */
        int label_match = gen_new_label();
        arm_gen_test_cc(cond, label_match);
        gen_goto_tb(s, 0, s->pc);
        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);
    }
1025
1026
}

1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
/* C5.6.68 HINT */
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 0: /* NOP */
        return;
    case 1: /* YIELD */
    case 2: /* WFE */
    case 3: /* WFI */
    case 4: /* SEV */
    case 5: /* SEVL */
        /* we treat all as NOP at least for now */
        return;
    default:
        /* default specified as NOP equivalent */
        return;
    }
}

1054
1055
1056
1057
1058
static void gen_clrex(DisasContext *s, uint32_t insn)
{
    tcg_gen_movi_i64(cpu_exclusive_addr, -1);
}

1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
/* CLREX, DSB, DMB, ISB */
static void handle_sync(DisasContext *s, uint32_t insn,
                        unsigned int op1, unsigned int op2, unsigned int crm)
{
    if (op1 != 3) {
        unallocated_encoding(s);
        return;
    }

    switch (op2) {
    case 2: /* CLREX */
1070
        gen_clrex(s, insn);
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
        return;
    case 4: /* DSB */
    case 5: /* DMB */
    case 6: /* ISB */
        /* We don't emulate caches so barriers are no-ops */
        return;
    default:
        unallocated_encoding(s);
        return;
    }
}

/* C5.6.130 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)
{
    unsupported_encoding(s, insn);
}

1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
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, (1 << 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_trunc_i64_i32(nzcv, tcg_rt);

    /* bit 31, N */
    tcg_gen_andi_i32(cpu_NF, nzcv, (1 << 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);
}

1134
1135
1136
1137
1138
1139
1140
1141
1142
/* C5.6.129 MRS - move from system register
 * C5.6.131 MSR (register) - move to system register
 * C5.6.204 SYS
 * C5.6.205 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,
1143
1144
                       unsigned int crn, unsigned int crm, unsigned int rt)
{
1145
1146
    const ARMCPRegInfo *ri;
    TCGv_i64 tcg_rt;
1147

1148
1149
1150
    ri = get_arm_cp_reginfo(s->cp_regs,
                            ENCODE_AA64_CP_REG(CP_REG_ARM64_SYSREG_CP,
                                               crn, crm, op0, op1, op2));
1151

1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
    if (!ri) {
        /* Unknown register */
        unallocated_encoding(s);
        return;
    }

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

    /* Handle special cases first */
    switch (ri->type & ~(ARM_CP_FLAG_MASK & ~ARM_CP_SPECIAL)) {
    case ARM_CP_NOP:
        return;
1168
1169
1170
1171
1172
1173
1174
1175
    case ARM_CP_NZCV:
        tcg_rt = cpu_reg(s, rt);
        if (isread) {
            gen_get_nzcv(tcg_rt);
        } else {
            gen_set_nzcv(tcg_rt);
        }
        return;
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
    default:
        break;
    }

    if (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;
            gen_a64_set_pc_im(s->pc - 4);
            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;
            gen_a64_set_pc_im(s->pc - 4);
            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 (use_icount && (ri->type & ARM_CP_IO)) {
        /* I/O operations must end the TB here (whether read or write) */
        gen_io_end();
        s->is_jmp = DISAS_UPDATE;
    } else if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) {
        /* 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->is_jmp = DISAS_UPDATE;
    }
1224
1225
}

1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
/* C3.2.4 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: /* C5.6.68 HINT */
            handle_hint(s, insn, op1, op2, crm);
            break;
        case 3: /* CLREX, DSB, DMB, ISB */
            handle_sync(s, insn, op1, op2, crm);
            break;
        case 4: /* C5.6.130 MSR (immediate) */
            handle_msr_i(s, insn, op1, op2, crm);
            break;
        default:
            unallocated_encoding(s);
            break;
        }
        return;
    }
1264
    handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt);
1265
1266
}

1267
1268
1269
1270
1271
1272
1273
/* C3.2.3 Exception generation
 *
 *  31             24 23 21 20                     5 4   2 1  0
 * +-----------------+-----+------------------------+-----+----+
 * | 1 1 0 1 0 1 0 0 | opc |          imm16         | op2 | LL |
 * +-----------------------+------------------------+----------+
 */
1274
1275
static void disas_exc(DisasContext *s, uint32_t insn)
{
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
    int opc = extract32(insn, 21, 3);
    int op2_ll = extract32(insn, 0, 5);

    switch (opc) {
    case 0:
        /* SVC, HVC, SMC; since we don't support the Virtualization
         * or TrustZone extensions these all UNDEF except SVC.
         */
        if (op2_ll != 1) {
            unallocated_encoding(s);
            break;
        }
        gen_exception_insn(s, 0, EXCP_SWI);
        break;
    case 1:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* BRK */
        gen_exception_insn(s, 0, EXCP_BKPT);
        break;
    case 2:
        if (op2_ll != 0) {
            unallocated_encoding(s);
            break;
        }
        /* HLT */
        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;
    }
1318
1319
}

1320
1321
1322
1323
1324
1325
/* C3.2.7 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  |
 * +---------------+-------+-------+-------+------+-------+
 */
1326
1327
static void disas_uncond_b_reg(DisasContext *s, uint32_t insn)
{
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
    unsigned int opc, op2, op3, rn, op4;

    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 (op4 != 0x0 || op3 != 0x0 || op2 != 0x1f) {
        unallocated_encoding(s);
        return;
    }

    switch (opc) {
    case 0: /* BR */
    case 2: /* RET */
        break;
    case 1: /* BLR */
        tcg_gen_movi_i64(cpu_reg(s, 30), s->pc);
        break;
    case 4: /* ERET */
    case 5: /* DRPS */
        if (rn != 0x1f) {
            unallocated_encoding(s);
        } else {
            unsupported_encoding(s, insn);
        }
        return;
    default:
        unallocated_encoding(s);
        return;
    }

    tcg_gen_mov_i64(cpu_pc, cpu_reg(s, rn));
    s->is_jmp = DISAS_JUMP;
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
}

/* C3.2 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)) {
            disas_system(s, insn);
        } else {
            disas_exc(s, insn);
        }
        break;
    case 0x6b: /* Unconditional branch (register) */
        disas_uncond_b_reg(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
/*
 * 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.
 *
 * In system emulation mode only one CPU will be running at once, so
 * this sequence is effectively atomic.  In user emulation mode we
 * throw an exception and handle the atomic operation elsewhere.
 */
static void gen_load_exclusive(DisasContext *s, int rt, int rt2,
                               TCGv_i64 addr, int size, bool is_pair)
{
    TCGv_i64 tmp = tcg_temp_new_i64();
    TCGMemOp memop = MO_TE + size;

    g_assert(size <= 3);
    tcg_gen_qemu_ld_i64(tmp, addr, get_mem_index(s), memop);

    if (is_pair) {
        TCGv_i64 addr2 = tcg_temp_new_i64();
        TCGv_i64 hitmp = tcg_temp_new_i64();

        g_assert(size >= 2);
        tcg_gen_addi_i64(addr2, addr, 1 << size);
        tcg_gen_qemu_ld_i64(hitmp, addr2, get_mem_index(s), memop);
        tcg_temp_free_i64(addr2);
        tcg_gen_mov_i64(cpu_exclusive_high, hitmp);
        tcg_gen_mov_i64(cpu_reg(s, rt2), hitmp);
        tcg_temp_free_i64(hitmp);
    }

    tcg_gen_mov_i64(cpu_exclusive_val, tmp);
    tcg_gen_mov_i64(cpu_reg(s, rt), tmp);

    tcg_temp_free_i64(tmp);
    tcg_gen_mov_i64(cpu_exclusive_addr, addr);
}

#ifdef CONFIG_USER_ONLY
static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
                                TCGv_i64 addr, int size, int is_pair)
{
    tcg_gen_mov_i64(cpu_exclusive_test, addr);
    tcg_gen_movi_i32(cpu_exclusive_info,
                     size | is_pair << 2 | (rd << 4) | (rt << 9) | (rt2 << 14));
    gen_exception_insn(s, 4, EXCP_STREX);
}
#else
static void gen_store_exclusive(DisasContext *s, int rd, int rt, int rt2,
                                TCGv_i64 addr, int size, int is_pair)
{
    qemu_log_mask(LOG_UNIMP,
                  "%s:%d: system mode store_exclusive unsupported "
                  "at pc=%016" PRIx64 "\n",
                  __FILE__, __LINE__, s->pc - 4);
}
#endif

/* C3.3.6 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
 *
 *  o0 == 0 AND o2 == 1 is un-allocated
 *  o1 == 1 is un-allocated except for 32 and 64 bit sizes
 */
1474
1475
static void disas_ldst_excl(DisasContext *s, uint32_t insn)
{
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    int is_lasr = extract32(insn, 15, 1);
    int rs = extract32(insn, 16, 5);
    int is_pair = extract32(insn, 21, 1);
    int is_store = !extract32(insn, 22, 1);
    int is_excl = !extract32(insn, 23, 1);
    int size = extract32(insn, 30, 2);
    TCGv_i64 tcg_addr;

    if ((!is_excl && !is_lasr) ||
        (is_pair && size < 2)) {
        unallocated_encoding(s);
        return;
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    /* Note that since TCG is single threaded load-acquire/store-release
     * semantics require no extra if (is_lasr) { ... } handling.
     */

    if (is_excl) {
        if (!is_store) {
            gen_load_exclusive(s, rt, rt2, tcg_addr, size, is_pair);
        } else {
            gen_store_exclusive(s, rs, rt, rt2, tcg_addr, size, is_pair);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, false, false);
        }
        if (is_pair) {
            TCGv_i64 tcg_rt2 = cpu_reg(s, rt);
            tcg_gen_addi_i64(tcg_addr, tcg_addr, 1 << size);
            if (is_store) {
                do_gpr_st(s, tcg_rt2, tcg_addr, size);
            } else {
                do_gpr_ld(s, tcg_rt2, tcg_addr, size, false, false);
            }
        }
    }
1525
1526
}

1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
/*
 * C3.3.5 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)
 */
1540
1541
static void disas_ld_lit(DisasContext *s, uint32_t insn)
{
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
    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, tcg_addr;

    if (is_vector) {
        if (opc == 3) {
            unallocated_encoding(s);
            return;
        }
        size = 2 + opc;
    } 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);

    tcg_addr = tcg_const_i64((s->pc - 4) + imm);
    if (is_vector) {
        do_fp_ld(s, rt, tcg_addr, size);
    } else {
        do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, false);
    }
    tcg_temp_free_i64(tcg_addr);
1574
1575
}

1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
/*
 * C5.6.80 LDNP (Load Pair - non-temporal hint)
 * C5.6.81 LDP (Load Pair - non vector)
 * C5.6.82 LDPSW (Load Pair Signed Word - non vector)
 * C5.6.176 STNP (Store Pair - non-temporal hint)
 * C5.6.177 STP (Store Pair - non vector)
 * C6.3.165 LDNP (Load Pair of SIMD&FP - non-temporal hint)
 * C6.3.165 LDP (Load Pair of SIMD&FP)
 * C6.3.284 STNP (Store Pair of SIMD&FP - non-temporal hint)
 * C6.3.284 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                    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)
 */
1604
1605
static void disas_ldst_pair(DisasContext *s, uint32_t insn)
{
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int rt2 = extract32(insn, 10, 5);
    int64_t offset = sextract32(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;

    TCGv_i64 tcg_addr; /* calculated address */
    int size;

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

    if (is_vector) {
        size = 2 + opc;
    } 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;
    }

    offset <<= size;

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

    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    if (!postindex) {
        tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);
    }

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

    if (wback) {
        if (postindex) {
            tcg_gen_addi_i64(tcg_addr, tcg_addr, offset - (1 << size));
        } else {
            tcg_gen_subi_i64(tcg_addr, tcg_addr, 1 << size);
        }
        tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr);
    }
1715
1716
}

1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
/*
 * C3.3.8 Load/store (immediate post-indexed)
 * C3.3.9 Load/store (immediate pre-indexed)
 * C3.3.12 Load/store (unscaled immediate)
 *
 * 31 30 29   27  26 25 24 23 22 21  20    12 11 10 9    5 4    0
 * +----+-------+---+-----+-----+---+--------+-----+------+------+
 * |size| 1 1 1 | V | 0 0 | opc | 0 |  imm9  | idx |  Rn  |  Rt  |
 * +----+-------+---+-----+-----+---+--------+-----+------+------+
 *
 * idx = 01 -> post-indexed, 11 pre-indexed, 00 unscaled imm. (no writeback)
 * V = 0 -> non-vector
 * size: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64bit
 * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 */
static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int imm9 = sextract32(insn, 12, 9);
    int opc = extract32(insn, 22, 2);
    int size = extract32(insn, 30, 2);
    int idx = extract32(insn, 10, 2);
    bool is_signed = false;
    bool is_store = false;
    bool is_extended = false;
    bool is_vector = extract32(insn, 26, 1);
    bool post_index;
    bool writeback;

    TCGv_i64 tcg_addr;

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4) {
            unallocated_encoding(s);
            return;
        }
        is_store = ((opc & 1) == 0);
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = opc & (1<<1);
        is_extended = (size < 3) && (opc & 1);
    }

    switch (idx) {
    case 0:
        post_index = false;
        writeback = false;
        break;
    case 1:
        post_index = true;
        writeback = true;
        break;
    case 3:
        post_index = false;
        writeback = true;
        break;
    case 2:
        g_assert(false);
        break;
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    if (!post_index) {
        tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
    }

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
        }
    }

    if (writeback) {
        TCGv_i64 tcg_rn = cpu_reg_sp(s, rn);
        if (post_index) {
            tcg_gen_addi_i64(tcg_addr, tcg_addr, imm9);
        }
        tcg_gen_mov_i64(tcg_rn, tcg_addr);
    }
}

1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
/*
 * C3.3.10 Load/store (register offset)
 *
 * 31 30 29   27  26 25 24 23 22 21  20  16 15 13 12 11 10 9  5 4  0
 * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
 * |size| 1 1 1 | V | 0 0 | opc | 1 |  Rm  | opt | S| 1 0 | Rn | Rt |
 * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+
 *
 * For non-vector:
 *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
 *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 * For vector:
 *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
 *   opc<0>: 0 -> store, 1 -> load
 * V: 1 -> vector/simd
 * opt: extend encoding (see DecodeRegExtend)
 * S: if S=1 then scale (essentially index by sizeof(size))
 * Rt: register to transfer into/out of
 * Rn: address register or SP for base
 * Rm: offset register or ZR for offset
 */
static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int shift = extract32(insn, 12, 1);
    int rm = extract32(insn, 16, 5);
    int opc = extract32(insn, 22, 2);
    int opt = extract32(insn, 13, 3);
    int size = extract32(insn, 30, 2);
    bool is_signed = false;
    bool is_store = false;
    bool is_extended = false;
    bool is_vector = extract32(insn, 26, 1);

    TCGv_i64 tcg_rm;
    TCGv_i64 tcg_addr;

    if (extract32(opt, 1, 1) == 0) {
        unallocated_encoding(s);
        return;
    }

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4) {
            unallocated_encoding(s);
            return;
        }
        is_store = !extract32(opc, 0, 1);
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = extract32(opc, 1, 1);
        is_extended = (size < 3) && extract32(opc, 0, 1);
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);

    tcg_rm = read_cpu_reg(s, rm, 1);
    ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0);

    tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_rm);

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
        }
    }
}

1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
/*
 * C3.3.13 Load/store (unsigned immediate)
 *
 * 31 30 29   27  26 25 24 23 22 21        10 9     5
 * +----+-------+---+-----+-----+------------+-------+------+
 * |size| 1 1 1 | V | 0 1 | opc |   imm12    |  Rn   |  Rt  |
 * +----+-------+---+-----+-----+------------+-------+------+
 *
 * For non-vector:
 *   size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit
 *   opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32
 * For vector:
 *   size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated
 *   opc<0>: 0 -> store, 1 -> load
 * Rn: base address register (inc SP)
 * Rt: target register
 */
static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn)
{
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    unsigned int imm12 = extract32(insn, 10, 12);
    bool is_vector = extract32(insn, 26, 1);
    int size = extract32(insn, 30, 2);
    int opc = extract32(insn, 22, 2);
    unsigned int offset;

    TCGv_i64 tcg_addr;

    bool is_store;
    bool is_signed = false;
    bool is_extended = false;

    if (is_vector) {
        size |= (opc & 2) << 1;
        if (size > 4) {
            unallocated_encoding(s);
            return;
        }
        is_store = !extract32(opc, 0, 1);
    } else {
        if (size == 3 && opc == 2) {
            /* PRFM - prefetch */
            return;
        }
        if (opc == 3 && size > 1) {
            unallocated_encoding(s);
            return;
        }
        is_store = (opc == 0);
        is_signed = extract32(opc, 1, 1);
        is_extended = (size < 3) && extract32(opc, 0, 1);
    }

    if (rn == 31) {
        gen_check_sp_alignment(s);
    }
    tcg_addr = read_cpu_reg_sp(s, rn, 1);
    offset = imm12 << size;
    tcg_gen_addi_i64(tcg_addr, tcg_addr, offset);

    if (is_vector) {
        if (is_store) {
            do_fp_st(s, rt, tcg_addr, size);
        } else {
            do_fp_ld(s, rt, tcg_addr, size);
        }
    } else {
        TCGv_i64 tcg_rt = cpu_reg(s, rt);
        if (is_store) {
            do_gpr_st(s, tcg_rt, tcg_addr, size);
        } else {
            do_gpr_ld(s, tcg_rt, tcg_addr, size, is_signed, is_extended);
        }
    }
}

1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
/* Load/store register (immediate forms) */
static void disas_ldst_reg_imm(DisasContext *s, uint32_t insn)
{
    switch (extract32(insn, 10, 2)) {
    case 0: case 1: case 3:
        /* Load/store register (unscaled immediate) */
        /* Load/store immediate pre/post-indexed */
        disas_ldst_reg_imm9(s, insn);
        break;
    case 2:
        /* Load/store register unprivileged */
        unsupported_encoding(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
}

2007
2008
2009
/* Load/store register (all forms) */
static void disas_ldst_reg(DisasContext *s, uint32_t insn)
{
2010
2011
    switch (extract32(insn, 24, 2)) {
    case 0:
2012
2013
2014
        if (extract32(insn, 21, 1) == 1 && extract32(insn, 10, 2) == 2) {
            disas_ldst_reg_roffset(s, insn);
        } else {
2015
            disas_ldst_reg_imm(s, insn);
2016
        }
2017
2018
2019
2020
2021
2022
2023
2024
        break;
    case 1:
        disas_ldst_reg_unsigned_imm(s, insn);
        break;
    default:
        unallocated_encoding(s);
        break;
    }
2025
2026
}

2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
/* C3.3.1 AdvSIMD load/store multiple structures
 *
 *  31  30  29           23 22  21         16 15    12 11  10 9    5 4    0
 * +---+---+---------------+---+-------------+--------+------+------+------+
 * | 0 | Q | 0 0 1 1 0 0 0 | L | 0 0 0 0 0 0 | opcode | size |  Rn  |  Rt  |
 * +---+---+---------------+---+-------------+--------+------+------+------+
 *
 * C3.3.2 AdvSIMD load/store multiple structures (post-indexed)
 *
 *  31  30  29           23 22  21  20     16 15    12 11  10 9    5 4    0
 * +---+---+---------------+---+---+---------+--------+------+------+------+
 * | 0 | Q | 0 0 1 1 0 0 1 | L | 0 |   Rm    | opcode | size |  Rn  |  Rt  |
 * +---+---+---------------+---+---+---------+--------+------+------+------+
 *
 * Rt: first (or only) SIMD&FP register to be transferred
 * Rn: base address or SP
 * Rm (post-index only): post-index register (when !31) or size dependent #imm
 */
2045
2046
static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn)
{
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int size = extract32(insn, 10, 2);
    int opcode = extract32(insn, 12, 4);
    bool is_store = !extract32(insn, 22, 1);
    bool is_postidx = extract32(insn, 23, 1);
    bool is_q = extract32(insn, 30, 1);
    TCGv_i64 tcg_addr, tcg_rn;

    int ebytes = 1 << size;
    int elements = (is_q ? 128 : 64) / (8 << size);
    int rpt;    /* num iterations */
    int selem;  /* structure elements */
    int r;

    if (extract32(insn, 31, 1) || extract32(insn, 21, 1)) {
        unallocated_encoding(s);
        return;
    }

    /* From the shared decode logic */
    switch (opcode) {
    case 0x0:
        rpt = 1;
        selem = 4;
        break;
    case 0x2:
        rpt = 4;
        selem = 1;
        break;
    case 0x4:
        rpt = 1;
        selem = 3;
        break;
    case 0x6:
        rpt = 3;
        selem = 1;
        break;
    case 0x7:
        rpt = 1;
        selem = 1;
        break;
    case 0x8:
        rpt = 1;
        selem = 2;
        break;
    case 0xa:
        rpt = 2;
        selem = 1;
        break;
    default:
        unallocated_encoding(s);
        return;
    }

    if (size == 3 && !is_q && selem != 1) {
        /* reserved */
        unallocated_encoding(s);
        return;
    }

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

    tcg_rn = cpu_reg_sp(s, rn);
    tcg_addr = tcg_temp_new_i64();
    tcg_gen_mov_i64(tcg_addr, tcg_rn);

    for (r = 0; r < rpt; r++) {
        int e;
        for (e = 0; e < elements; e++) {
            int tt = (rt + r) % 32;
            int xs;
            for (xs = 0; xs < selem; xs++) {
                if (is_store) {
                    do_vec_st(s, tt, e, tcg_addr, size);
                } else {
                    do_vec_ld(s, tt, e, tcg_addr, size);

                    /* For non-quad operations, setting a slice of the low
                     * 64 bits of the register clears the high 64 bits (in
                     * the ARM ARM pseudocode this is implicit in the fact
                     * that 'rval' is a 64 bit wide variable). We optimize
                     * by noticing that we only need to do this the first
                     * time we touch a register.
                     */
                    if (!is_q && e == 0 && (r == 0 || xs == selem - 1)) {
                        clear_vec_high(s, tt);
                    }
                }
                tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
                tt = (tt + 1) % 32;
            }
        }
    }

    if (is_postidx) {
        int rm = extract32(insn, 16, 5);
        if (rm == 31) {
            tcg_gen_mov_i64(tcg_rn, tcg_addr);
        } else {
            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
        }
    }
    tcg_temp_free_i64(tcg_addr);
2153
2154
}

2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
/* C3.3.3 AdvSIMD load/store single structure
 *
 *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size |  Rn  |  Rt  |
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 *
 * C3.3.4 AdvSIMD load/store single structure (post-indexed)
 *
 *  31  30  29           23 22 21 20       16 15 13 12  11  10 9    5 4    0
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 * | 0 | Q | 0 0 1 1 0 1 1 | L R |     Rm    | opc | S | size |  Rn  |  Rt  |
 * +---+---+---------------+-----+-----------+-----+---+------+------+------+
 *
 * Rt: first (or only) SIMD&FP register to be transferred
 * Rn: base address or SP
 * Rm (post-index only): post-index register (when !31) or size dependent #imm
 * index = encoded in Q:S:size dependent on size
 *
 * lane_size = encoded in R, opc
 * transfer width = encoded in opc, S, size
 */
2177
2178
static void disas_ldst_single_struct(DisasContext *s, uint32_t insn)
{
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
    int rt = extract32(insn, 0, 5);
    int rn = extract32(insn, 5, 5);
    int size = extract32(insn, 10, 2);
    int S = extract32(insn, 12, 1);
    int opc = extract32(insn, 13, 3);
    int R = extract32(insn, 21, 1);
    int is_load = extract32(insn, 22, 1);
    int is_postidx = extract32(insn, 23, 1);
    int is_q = extract32(insn, 30, 1);

    int scale = extract32(opc, 1, 2);
    int selem = (extract32(opc, 0, 1) << 1 | R) + 1;
    bool replicate = false;
    int index = is_q << 3 | S << 2 | size;
    int ebytes, xs;
    TCGv_i64 tcg_addr, tcg_rn;

    switch (scale) {
    case 3:
        if (!is_load || S) {
            unallocated_encoding(s);
            return;
        }
        scale = size;
        replicate = true;
        break;
    case 0:
        break;
    case 1:
        if (extract32(size, 0, 1)) {
            unallocated_encoding(s);
            return;
        }
        index >>= 1;
        break;
    case 2:
        if (extract32(size, 1, 1)) {
            unallocated_encoding(s);
            return;
        }
        if (!extract32(size, 0, 1)) {
            index >>= 2;
        } else {
            if (S) {
                unallocated_encoding(s);
                return;
            }
            index >>= 3;
            scale = 3;
        }
        break;
    default:
        g_assert_not_reached();
    }

    ebytes = 1 << scale;

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

    tcg_rn = cpu_reg_sp(s, rn);
    tcg_addr = tcg_temp_new_i64();
    tcg_gen_mov_i64(tcg_addr, tcg_rn);

    for (xs = 0; xs < selem; xs++) {
        if (replicate) {
            /* Load and replicate to all elements */
            uint64_t mulconst;
            TCGv_i64 tcg_tmp = tcg_temp_new_i64();

            tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr,
                                get_mem_index(s), MO_TE + scale);
            switch (scale) {
            case 0:
                mulconst = 0x0101010101010101ULL;
                break;
            case 1:
                mulconst = 0x0001000100010001ULL;
                break;
            case 2:
                mulconst = 0x0000000100000001ULL;
                break;
            case 3:
                mulconst = 0;
                break;
            default:
                g_assert_not_reached();
            }
            if (mulconst) {
                tcg_gen_muli_i64(tcg_tmp, tcg_tmp, mulconst);
            }
            write_vec_element(s, tcg_tmp, rt, 0, MO_64);
            if (is_q) {
                write_vec_element(s, tcg_tmp, rt, 1, MO_64);
            } else {
                clear_vec_high(s, rt);
            }
            tcg_temp_free_i64(tcg_tmp);
        } else {
            /* Load/store one element per register */
            if (is_load) {
                do_vec_ld(s, rt, index, tcg_addr, MO_TE + scale);
            } else {
                do_vec_st(s, rt, index, tcg_addr, MO_TE + scale);
            }
        }
        tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes);
        rt = (rt + 1) % 32;
    }

    if (is_postidx) {
        int rm = extract32(insn, 16, 5);
        if (rm == 31) {
            tcg_gen_mov_i64(tcg_rn, tcg_addr);
        } else {
            tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm));
        }
    }
    tcg_temp_free_i64(tcg_addr);
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318