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
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
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
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
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
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
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
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
|
/*
* ARM helper routines
*
* Copyright (c) 2005-2007 CodeSourcery, LLC
*
* This library is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This library is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with this library; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301 USA
*/
#include "exec.h"
#include "helpers.h"
#define SIGNBIT (uint32_t)0x80000000
#define SIGNBIT64 ((uint64_t)1 << 63)
void raise_exception(int tt)
{
env->exception_index = tt;
cpu_loop_exit();
}
/* thread support */
static spinlock_t global_cpu_lock = SPIN_LOCK_UNLOCKED;
void cpu_lock(void)
{
spin_lock(&global_cpu_lock);
}
void cpu_unlock(void)
{
spin_unlock(&global_cpu_lock);
}
uint32_t HELPER(neon_tbl)(uint32_t ireg, uint32_t def,
uint32_t rn, uint32_t maxindex)
{
uint32_t val;
uint32_t tmp;
int index;
int shift;
uint64_t *table;
table = (uint64_t *)&env->vfp.regs[rn];
val = 0;
for (shift = 0; shift < 32; shift += 8) {
index = (ireg >> shift) & 0xff;
if (index < maxindex) {
tmp = (table[index >> 3] >> ((index & 7) << 3)) & 0xff;
val |= tmp << shift;
} else {
val |= def & (0xff << shift);
}
}
return val;
}
#if !defined(CONFIG_USER_ONLY)
//#define ALIGNED_ONLY 1
#if ALIGNED_ONLY == 1
static void do_unaligned_access (target_ulong addr, int is_write, int is_user, void *retaddr);
#endif
#define MMUSUFFIX _mmu
#define SHIFT 0
#include "softmmu_template.h"
#define SHIFT 1
#include "softmmu_template.h"
#define SHIFT 2
#include "softmmu_template.h"
#define SHIFT 3
#include "softmmu_template.h"
#if ALIGNED_ONLY == 1
static void do_unaligned_access (target_ulong addr, int is_write, int mmu_idx, void *retaddr)
{
//printf("::UNALIGNED:: addr=%lx is_write=%d is_user=%d retaddr=%p\n", addr, is_write, is_user, retaddr);
if (mmu_idx)
{
env = cpu_single_env;
env->cp15.c5_data = 0x00000001; /* corresponds to an alignment fault */
env->cp15.c6_data = addr;
env->exception_index = EXCP_DATA_ABORT;
cpu_loop_exit();
}
}
#endif
/* try to fill the TLB and return an exception if error. If retaddr is
NULL, it means that the function was called in C code (i.e. not
from generated code or from helper.c) */
/* XXX: fix it to restore all registers */
void tlb_fill (target_ulong addr, int is_write, int mmu_idx, void *retaddr)
{
TranslationBlock *tb;
CPUState *saved_env;
unsigned long pc;
int ret;
/* XXX: hack to restore env in all cases, even if not called from
generated code */
saved_env = env;
env = cpu_single_env;
ret = cpu_arm_handle_mmu_fault(env, addr, is_write, mmu_idx, 1);
if (unlikely(ret)) {
if (retaddr) {
/* now we have a real cpu fault */
pc = (unsigned long)retaddr;
tb = tb_find_pc(pc);
if (tb) {
/* the PC is inside the translated code. It means that we have
a virtual CPU fault */
cpu_restore_state(tb, env, pc, NULL);
}
}
raise_exception(env->exception_index);
}
env = saved_env;
}
/* copy a string from the simulated virtual space to a buffer in QEMU */
void vstrcpy(target_ulong ptr, char *buf, int max)
{
int index;
if (buf == NULL) return;
for (index = 0; index < max; index += 1) {
cpu_physical_memory_read(ptr + index, (uint8_t*)buf + index, 1);
if (buf[index] == 0)
break;
}
}
#endif
/* FIXME: Pass an axplicit pointer to QF to CPUState, and move saturating
instructions into helper.c */
uint32_t HELPER(add_setq)(uint32_t a, uint32_t b)
{
uint32_t res = a + b;
if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT))
env->QF = 1;
return res;
}
uint32_t HELPER(add_saturate)(uint32_t a, uint32_t b)
{
uint32_t res = a + b;
if (((res ^ a) & SIGNBIT) && !((a ^ b) & SIGNBIT)) {
env->QF = 1;
res = ~(((int32_t)a >> 31) ^ SIGNBIT);
}
return res;
}
uint32_t HELPER(sub_saturate)(uint32_t a, uint32_t b)
{
uint32_t res = a - b;
if (((res ^ a) & SIGNBIT) && ((a ^ b) & SIGNBIT)) {
env->QF = 1;
res = ~(((int32_t)a >> 31) ^ SIGNBIT);
}
return res;
}
uint32_t HELPER(double_saturate)(int32_t val)
{
uint32_t res;
if (val >= 0x40000000) {
res = ~SIGNBIT;
env->QF = 1;
} else if (val <= (int32_t)0xc0000000) {
res = SIGNBIT;
env->QF = 1;
} else {
res = val << 1;
}
return res;
}
uint32_t HELPER(add_usaturate)(uint32_t a, uint32_t b)
{
uint32_t res = a + b;
if (res < a) {
env->QF = 1;
res = ~0;
}
return res;
}
uint32_t HELPER(sub_usaturate)(uint32_t a, uint32_t b)
{
uint32_t res = a - b;
if (res > a) {
env->QF = 1;
res = 0;
}
return res;
}
/* Signed saturation. */
static inline uint32_t do_ssat(int32_t val, int shift)
{
int32_t top;
uint32_t mask;
top = val >> shift;
mask = (1u << shift) - 1;
if (top > 0) {
env->QF = 1;
return mask;
} else if (top < -1) {
env->QF = 1;
return ~mask;
}
return val;
}
/* Unsigned saturation. */
static inline uint32_t do_usat(int32_t val, int shift)
{
uint32_t max;
max = (1u << shift) - 1;
if (val < 0) {
env->QF = 1;
return 0;
} else if (val > max) {
env->QF = 1;
return max;
}
return val;
}
/* Signed saturate. */
uint32_t HELPER(ssat)(uint32_t x, uint32_t shift)
{
return do_ssat(x, shift);
}
/* Dual halfword signed saturate. */
uint32_t HELPER(ssat16)(uint32_t x, uint32_t shift)
{
uint32_t res;
res = (uint16_t)do_ssat((int16_t)x, shift);
res |= do_ssat(((int32_t)x) >> 16, shift) << 16;
return res;
}
/* Unsigned saturate. */
uint32_t HELPER(usat)(uint32_t x, uint32_t shift)
{
return do_usat(x, shift);
}
/* Dual halfword unsigned saturate. */
uint32_t HELPER(usat16)(uint32_t x, uint32_t shift)
{
uint32_t res;
res = (uint16_t)do_usat((int16_t)x, shift);
res |= do_usat(((int32_t)x) >> 16, shift) << 16;
return res;
}
void HELPER(wfi)(void)
{
env->exception_index = EXCP_HLT;
env->halted = 1;
cpu_loop_exit();
}
void HELPER(exception)(uint32_t excp)
{
env->exception_index = excp;
cpu_loop_exit();
}
uint32_t HELPER(cpsr_read)(void)
{
return cpsr_read(env) & ~CPSR_EXEC;
}
void HELPER(cpsr_write)(uint32_t val, uint32_t mask)
{
cpsr_write(env, val, mask);
}
/* Access to user mode registers from privileged modes. */
uint32_t HELPER(get_user_reg)(uint32_t regno)
{
uint32_t val;
if (regno == 13) {
val = env->banked_r13[0];
} else if (regno == 14) {
val = env->banked_r14[0];
} else if (regno >= 8
&& (env->uncached_cpsr & 0x1f) == ARM_CPU_MODE_FIQ) {
val = env->usr_regs[regno - 8];
} else {
val = env->regs[regno];
}
return val;
}
void HELPER(set_user_reg)(uint32_t regno, uint32_t val)
{
if (regno == 13) {
env->banked_r13[0] = val;
} else if (regno == 14) {
env->banked_r14[0] = val;
} else if (regno >= 8
&& (env->uncached_cpsr & 0x1f) == ARM_CPU_MODE_FIQ) {
env->usr_regs[regno - 8] = val;
} else {
env->regs[regno] = val;
}
}
/* ??? Flag setting arithmetic is awkward because we need to do comparisons.
The only way to do that in TCG is a conditional branch, which clobbers
all our temporaries. For now implement these as helper functions. */
uint32_t HELPER (add_cc)(uint32_t a, uint32_t b)
{
uint32_t result;
result = a + b;
env->NF = env->ZF = result;
env->CF = result < a;
env->VF = (a ^ b ^ -1) & (a ^ result);
return result;
}
uint32_t HELPER(adc_cc)(uint32_t a, uint32_t b)
{
uint32_t result;
if (!env->CF) {
result = a + b;
env->CF = result < a;
} else {
result = a + b + 1;
env->CF = result <= a;
}
env->VF = (a ^ b ^ -1) & (a ^ result);
env->NF = env->ZF = result;
return result;
}
uint32_t HELPER(sub_cc)(uint32_t a, uint32_t b)
{
uint32_t result;
result = a - b;
env->NF = env->ZF = result;
env->CF = a >= b;
env->VF = (a ^ b) & (a ^ result);
return result;
}
uint32_t HELPER(sbc_cc)(uint32_t a, uint32_t b)
{
uint32_t result;
if (!env->CF) {
result = a - b - 1;
env->CF = a > b;
} else {
result = a - b;
env->CF = a >= b;
}
env->VF = (a ^ b) & (a ^ result);
env->NF = env->ZF = result;
return result;
}
/* Similarly for variable shift instructions. */
uint32_t HELPER(shl)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32)
return 0;
return x << shift;
}
uint32_t HELPER(shr)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32)
return 0;
return (uint32_t)x >> shift;
}
uint32_t HELPER(sar)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32)
shift = 31;
return (int32_t)x >> shift;
}
uint32_t HELPER(ror)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift == 0)
return x;
return (x >> shift) | (x << (32 - shift));
}
uint32_t HELPER(shl_cc)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32) {
if (shift == 32)
env->CF = x & 1;
else
env->CF = 0;
return 0;
} else if (shift != 0) {
env->CF = (x >> (32 - shift)) & 1;
return x << shift;
}
return x;
}
uint32_t HELPER(shr_cc)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32) {
if (shift == 32)
env->CF = (x >> 31) & 1;
else
env->CF = 0;
return 0;
} else if (shift != 0) {
env->CF = (x >> (shift - 1)) & 1;
return x >> shift;
}
return x;
}
uint32_t HELPER(sar_cc)(uint32_t x, uint32_t i)
{
int shift = i & 0xff;
if (shift >= 32) {
env->CF = (x >> 31) & 1;
return (int32_t)x >> 31;
} else if (shift != 0) {
env->CF = (x >> (shift - 1)) & 1;
return (int32_t)x >> shift;
}
return x;
}
uint32_t HELPER(ror_cc)(uint32_t x, uint32_t i)
{
int shift1, shift;
shift1 = i & 0xff;
shift = shift1 & 0x1f;
if (shift == 0) {
if (shift1 != 0)
env->CF = (x >> 31) & 1;
return x;
} else {
env->CF = (x >> (shift - 1)) & 1;
return ((uint32_t)x >> shift) | (x << (32 - shift));
}
}
uint64_t HELPER(neon_add_saturate_s64)(uint64_t src1, uint64_t src2)
{
uint64_t res;
res = src1 + src2;
if (((res ^ src1) & SIGNBIT64) && !((src1 ^ src2) & SIGNBIT64)) {
env->QF = 1;
res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
}
return res;
}
uint64_t HELPER(neon_add_saturate_u64)(uint64_t src1, uint64_t src2)
{
uint64_t res;
res = src1 + src2;
if (res < src1) {
env->QF = 1;
res = ~(uint64_t)0;
}
return res;
}
uint64_t HELPER(neon_sub_saturate_s64)(uint64_t src1, uint64_t src2)
{
uint64_t res;
res = src1 - src2;
if (((res ^ src1) & SIGNBIT64) && ((src1 ^ src2) & SIGNBIT64)) {
env->QF = 1;
res = ((int64_t)src1 >> 63) ^ ~SIGNBIT64;
}
return res;
}
uint64_t HELPER(neon_sub_saturate_u64)(uint64_t src1, uint64_t src2)
{
uint64_t res;
if (src1 < src2) {
env->QF = 1;
res = 0;
} else {
res = src1 - src2;
}
return res;
}
/* These need to return a pair of value, so still use T0/T1. */
/* Transpose. Argument order is rather strange to avoid special casing
the tranlation code.
On input T0 = rm, T1 = rd. On output T0 = rd, T1 = rm */
void HELPER(neon_trn_u8)(void)
{
uint32_t rd;
uint32_t rm;
rd = ((T0 & 0x00ff00ff) << 8) | (T1 & 0x00ff00ff);
rm = ((T1 & 0xff00ff00) >> 8) | (T0 & 0xff00ff00);
T0 = rd;
T1 = rm;
}
void HELPER(neon_trn_u16)(void)
{
uint32_t rd;
uint32_t rm;
rd = (T0 << 16) | (T1 & 0xffff);
rm = (T1 >> 16) | (T0 & 0xffff0000);
T0 = rd;
T1 = rm;
}
/* Worker routines for zip and unzip. */
void HELPER(neon_unzip_u8)(void)
{
uint32_t rd;
uint32_t rm;
rd = (T0 & 0xff) | ((T0 >> 8) & 0xff00)
| ((T1 << 16) & 0xff0000) | ((T1 << 8) & 0xff000000);
rm = ((T0 >> 8) & 0xff) | ((T0 >> 16) & 0xff00)
| ((T1 << 8) & 0xff0000) | (T1 & 0xff000000);
T0 = rd;
T1 = rm;
}
void HELPER(neon_zip_u8)(void)
{
uint32_t rd;
uint32_t rm;
rd = (T0 & 0xff) | ((T1 << 8) & 0xff00)
| ((T0 << 16) & 0xff0000) | ((T1 << 24) & 0xff000000);
rm = ((T0 >> 16) & 0xff) | ((T1 >> 8) & 0xff00)
| ((T0 >> 8) & 0xff0000) | (T1 & 0xff000000);
T0 = rd;
T1 = rm;
}
void HELPER(neon_zip_u16)(void)
{
uint32_t tmp;
tmp = (T0 & 0xffff) | (T1 << 16);
T1 = (T1 & 0xffff0000) | (T0 >> 16);
T0 = tmp;
}
|