aboutsummaryrefslogtreecommitdiffstats
path: root/cpu-all.h
blob: 01e6838e5c7f51b5918da55cbc69d52e7968bfee (plain)
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
592
593
594
595
596
597
598
599
600
601
602
603
604
605
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
649
650
651
652
653
654
655
656
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
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
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
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
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
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
875
876
877
878
879
880
881
882
883
884
885
886
887
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
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
/*
 * defines common to all virtual CPUs
 *
 *  Copyright (c) 2003 Fabrice Bellard
 *
 * 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/>.
 */
#ifndef CPU_ALL_H
#define CPU_ALL_H

#include "qemu-common.h"
#include "cpu-common.h"

/* some important defines:
 *
 * WORDS_ALIGNED : if defined, the host cpu can only make word aligned
 * memory accesses.
 *
 * HOST_WORDS_BIGENDIAN : if defined, the host cpu is big endian and
 * otherwise little endian.
 *
 * (TARGET_WORDS_ALIGNED : same for target cpu (not supported yet))
 *
 * TARGET_WORDS_BIGENDIAN : same for target cpu
 */

#include "softfloat.h"

#if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN)
#define BSWAP_NEEDED
#endif

#ifdef BSWAP_NEEDED

static inline uint16_t tswap16(uint16_t s)
{
    return bswap16(s);
}

static inline uint32_t tswap32(uint32_t s)
{
    return bswap32(s);
}

static inline uint64_t tswap64(uint64_t s)
{
    return bswap64(s);
}

static inline void tswap16s(uint16_t *s)
{
    *s = bswap16(*s);
}

static inline void tswap32s(uint32_t *s)
{
    *s = bswap32(*s);
}

static inline void tswap64s(uint64_t *s)
{
    *s = bswap64(*s);
}

#else

static inline uint16_t tswap16(uint16_t s)
{
    return s;
}

static inline uint32_t tswap32(uint32_t s)
{
    return s;
}

static inline uint64_t tswap64(uint64_t s)
{
    return s;
}

static inline void tswap16s(uint16_t *s)
{
}

static inline void tswap32s(uint32_t *s)
{
}

static inline void tswap64s(uint64_t *s)
{
}

#endif

#if TARGET_LONG_SIZE == 4
#define tswapl(s) tswap32(s)
#define tswapls(s) tswap32s((uint32_t *)(s))
#define bswaptls(s) bswap32s(s)
#else
#define tswapl(s) tswap64(s)
#define tswapls(s) tswap64s((uint64_t *)(s))
#define bswaptls(s) bswap64s(s)
#endif

typedef union {
    float32 f;
    uint32_t l;
} CPU_FloatU;

/* NOTE: arm FPA is horrible as double 32 bit words are stored in big
   endian ! */
typedef union {
    float64 d;
#if defined(HOST_WORDS_BIGENDIAN) \
    || (defined(__arm__) && !defined(__VFP_FP__) && !defined(CONFIG_SOFTFLOAT))
    struct {
        uint32_t upper;
        uint32_t lower;
    } l;
#else
    struct {
        uint32_t lower;
        uint32_t upper;
    } l;
#endif
    uint64_t ll;
} CPU_DoubleU;

#ifdef TARGET_SPARC
typedef union {
    float128 q;
#if defined(HOST_WORDS_BIGENDIAN) \
    || (defined(__arm__) && !defined(__VFP_FP__) && !defined(CONFIG_SOFTFLOAT))
    struct {
        uint32_t upmost;
        uint32_t upper;
        uint32_t lower;
        uint32_t lowest;
    } l;
    struct {
        uint64_t upper;
        uint64_t lower;
    } ll;
#else
    struct {
        uint32_t lowest;
        uint32_t lower;
        uint32_t upper;
        uint32_t upmost;
    } l;
    struct {
        uint64_t lower;
        uint64_t upper;
    } ll;
#endif
} CPU_QuadU;
#endif

/* CPU memory access without any memory or io remapping */

/*
 * the generic syntax for the memory accesses is:
 *
 * load: ld{type}{sign}{size}{endian}_{access_type}(ptr)
 *
 * store: st{type}{size}{endian}_{access_type}(ptr, val)
 *
 * type is:
 * (empty): integer access
 *   f    : float access
 *
 * sign is:
 * (empty): for floats or 32 bit size
 *   u    : unsigned
 *   s    : signed
 *
 * size is:
 *   b: 8 bits
 *   w: 16 bits
 *   l: 32 bits
 *   q: 64 bits
 *
 * endian is:
 * (empty): target cpu endianness or 8 bit access
 *   r    : reversed target cpu endianness (not implemented yet)
 *   be   : big endian (not implemented yet)
 *   le   : little endian (not implemented yet)
 *
 * access_type is:
 *   raw    : host memory access
 *   user   : user mode access using soft MMU
 *   kernel : kernel mode access using soft MMU
 */
static inline int ldub_p(const void *ptr)
{
    return *(uint8_t *)ptr;
}

static inline int ldsb_p(const void *ptr)
{
    return *(int8_t *)ptr;
}

static inline void stb_p(void *ptr, int v)
{
    *(uint8_t *)ptr = v;
}

/* NOTE: on arm, putting 2 in /proc/sys/debug/alignment so that the
   kernel handles unaligned load/stores may give better results, but
   it is a system wide setting : bad */
#if defined(HOST_WORDS_BIGENDIAN) || defined(WORDS_ALIGNED)

/* conservative code for little endian unaligned accesses */
static inline int lduw_le_p(const void *ptr)
{
#ifdef _ARCH_PPC
    int val;
    __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (ptr));
    return val;
#else
    const uint8_t *p = ptr;
    return p[0] | (p[1] << 8);
#endif
}

static inline int ldsw_le_p(const void *ptr)
{
#ifdef _ARCH_PPC
    int val;
    __asm__ __volatile__ ("lhbrx %0,0,%1" : "=r" (val) : "r" (ptr));
    return (int16_t)val;
#else
    const uint8_t *p = ptr;
    return (int16_t)(p[0] | (p[1] << 8));
#endif
}

static inline int ldl_le_p(const void *ptr)
{
#ifdef _ARCH_PPC
    int val;
    __asm__ __volatile__ ("lwbrx %0,0,%1" : "=r" (val) : "r" (ptr));
    return val;
#else
    const uint8_t *p = ptr;
    return p[0] | (p[1] << 8) | (p[2] << 16) | (p[3] << 24);
#endif
}

static inline uint64_t ldq_le_p(const void *ptr)
{
    const uint8_t *p = ptr;
    uint32_t v1, v2;
    v1 = ldl_le_p(p);
    v2 = ldl_le_p(p + 4);
    return v1 | ((uint64_t)v2 << 32);
}

static inline void stw_le_p(void *ptr, int v)
{
#ifdef _ARCH_PPC
    __asm__ __volatile__ ("sthbrx %1,0,%2" : "=m" (*(uint16_t *)ptr) : "r" (v), "r" (ptr));
#else
    uint8_t *p = ptr;
    p[0] = v;
    p[1] = v >> 8;
#endif
}

static inline void stl_le_p(void *ptr, int v)
{
#ifdef _ARCH_PPC
    __asm__ __volatile__ ("stwbrx %1,0,%2" : "=m" (*(uint32_t *)ptr) : "r" (v), "r" (ptr));
#else
    uint8_t *p = ptr;
    p[0] = v;
    p[1] = v >> 8;
    p[2] = v >> 16;
    p[3] = v >> 24;
#endif
}

static inline void stq_le_p(void *ptr, uint64_t v)
{
    uint8_t *p = ptr;
    stl_le_p(p, (uint32_t)v);
    stl_le_p(p + 4, v >> 32);
}

/* float access */

static inline float32 ldfl_le_p(const void *ptr)
{
    union {
        float32 f;
        uint32_t i;
    } u;
    u.i = ldl_le_p(ptr);
    return u.f;
}

static inline void stfl_le_p(void *ptr, float32 v)
{
    union {
        float32 f;
        uint32_t i;
    } u;
    u.f = v;
    stl_le_p(ptr, u.i);
}

static inline float64 ldfq_le_p(const void *ptr)
{
    CPU_DoubleU u;
    u.l.lower = ldl_le_p(ptr);
    u.l.upper = ldl_le_p(ptr + 4);
    return u.d;
}

static inline void stfq_le_p(void *ptr, float64 v)
{
    CPU_DoubleU u;
    u.d = v;
    stl_le_p(ptr, u.l.lower);
    stl_le_p(ptr + 4, u.l.upper);
}

#else

static inline int lduw_le_p(const void *ptr)
{
    return *(uint16_t *)ptr;
}

static inline int ldsw_le_p(const void *ptr)
{
    return *(int16_t *)ptr;
}

static inline int ldl_le_p(const void *ptr)
{
    return *(uint32_t *)ptr;
}

static inline uint64_t ldq_le_p(const void *ptr)
{
    return *(uint64_t *)ptr;
}

static inline void stw_le_p(void *ptr, int v)
{
    *(uint16_t *)ptr = v;
}

static inline void stl_le_p(void *ptr, int v)
{
    *(uint32_t *)ptr = v;
}

static inline void stq_le_p(void *ptr, uint64_t v)
{
    *(uint64_t *)ptr = v;
}

/* float access */

static inline float32 ldfl_le_p(const void *ptr)
{
    return *(float32 *)ptr;
}

static inline float64 ldfq_le_p(const void *ptr)
{
    return *(float64 *)ptr;
}

static inline void stfl_le_p(void *ptr, float32 v)
{
    *(float32 *)ptr = v;
}

static inline void stfq_le_p(void *ptr, float64 v)
{
    *(float64 *)ptr = v;
}
#endif

#if !defined(HOST_WORDS_BIGENDIAN) || defined(WORDS_ALIGNED)

static inline int lduw_be_p(const void *ptr)
{
#if defined(__i386__)
    int val;
    asm volatile ("movzwl %1, %0\n"
                  "xchgb %b0, %h0\n"
                  : "=q" (val)
                  : "m" (*(uint16_t *)ptr));
    return val;
#else
    const uint8_t *b = ptr;
    return ((b[0] << 8) | b[1]);
#endif
}

static inline int ldsw_be_p(const void *ptr)
{
#if defined(__i386__)
    int val;
    asm volatile ("movzwl %1, %0\n"
                  "xchgb %b0, %h0\n"
                  : "=q" (val)
                  : "m" (*(uint16_t *)ptr));
    return (int16_t)val;
#else
    const uint8_t *b = ptr;
    return (int16_t)((b[0] << 8) | b[1]);
#endif
}

static inline int ldl_be_p(const void *ptr)
{
#if defined(__i386__) || defined(__x86_64__)
    int val;
    asm volatile ("movl %1, %0\n"
                  "bswap %0\n"
                  : "=r" (val)
                  : "m" (*(uint32_t *)ptr));
    return val;
#else
    const uint8_t *b = ptr;
    return (b[0] << 24) | (b[1] << 16) | (b[2] << 8) | b[3];
#endif
}

static inline uint64_t ldq_be_p(const void *ptr)
{
    uint32_t a,b;
    a = ldl_be_p(ptr);
    b = ldl_be_p((uint8_t *)ptr + 4);
    return (((uint64_t)a<<32)|b);
}

static inline void stw_be_p(void *ptr, int v)
{
#if defined(__i386__)
    asm volatile ("xchgb %b0, %h0\n"
                  "movw %w0, %1\n"
                  : "=q" (v)
                  : "m" (*(uint16_t *)ptr), "0" (v));
#else
    uint8_t *d = (uint8_t *) ptr;
    d[0] = v >> 8;
    d[1] = v;
#endif
}

static inline void stl_be_p(void *ptr, int v)
{
#if defined(__i386__) || defined(__x86_64__)
    asm volatile ("bswap %0\n"
                  "movl %0, %1\n"
                  : "=r" (v)
                  : "m" (*(uint32_t *)ptr), "0" (v));
#else
    uint8_t *d = (uint8_t *) ptr;
    d[0] = v >> 24;
    d[1] = v >> 16;
    d[2] = v >> 8;
    d[3] = v;
#endif
}

static inline void stq_be_p(void *ptr, uint64_t v)
{
    stl_be_p(ptr, v >> 32);
    stl_be_p((uint8_t *)ptr + 4, v);
}

/* float access */

static inline float32 ldfl_be_p(const void *ptr)
{
    union {
        float32 f;
        uint32_t i;
    } u;
    u.i = ldl_be_p(ptr);
    return u.f;
}

static inline void stfl_be_p(void *ptr, float32 v)
{
    union {
        float32 f;
        uint32_t i;
    } u;
    u.f = v;
    stl_be_p(ptr, u.i);
}

static inline float64 ldfq_be_p(const void *ptr)
{
    CPU_DoubleU u;
    u.l.upper = ldl_be_p(ptr);
    u.l.lower = ldl_be_p((uint8_t *)ptr + 4);
    return u.d;
}

static inline void stfq_be_p(void *ptr, float64 v)
{
    CPU_DoubleU u;
    u.d = v;
    stl_be_p(ptr, u.l.upper);
    stl_be_p((uint8_t *)ptr + 4, u.l.lower);
}

#else

static inline int lduw_be_p(const void *ptr)
{
    return *(uint16_t *)ptr;
}

static inline int ldsw_be_p(const void *ptr)
{
    return *(int16_t *)ptr;
}

static inline int ldl_be_p(const void *ptr)
{
    return *(uint32_t *)ptr;
}

static inline uint64_t ldq_be_p(const void *ptr)
{
    return *(uint64_t *)ptr;
}

static inline void stw_be_p(void *ptr, int v)
{
    *(uint16_t *)ptr = v;
}

static inline void stl_be_p(void *ptr, int v)
{
    *(uint32_t *)ptr = v;
}

static inline void stq_be_p(void *ptr, uint64_t v)
{
    *(uint64_t *)ptr = v;
}

/* float access */

static inline float32 ldfl_be_p(const void *ptr)
{
    return *(float32 *)ptr;
}

static inline float64 ldfq_be_p(const void *ptr)
{
    return *(float64 *)ptr;
}

static inline void stfl_be_p(void *ptr, float32 v)
{
    *(float32 *)ptr = v;
}

static inline void stfq_be_p(void *ptr, float64 v)
{
    *(float64 *)ptr = v;
}

#endif

/* target CPU memory access functions */
#if defined(TARGET_WORDS_BIGENDIAN)
#define lduw_p(p) lduw_be_p(p)
#define ldsw_p(p) ldsw_be_p(p)
#define ldl_p(p) ldl_be_p(p)
#define ldq_p(p) ldq_be_p(p)
#define ldfl_p(p) ldfl_be_p(p)
#define ldfq_p(p) ldfq_be_p(p)
#define stw_p(p, v) stw_be_p(p, v)
#define stl_p(p, v) stl_be_p(p, v)
#define stq_p(p, v) stq_be_p(p, v)
#define stfl_p(p, v) stfl_be_p(p, v)
#define stfq_p(p, v) stfq_be_p(p, v)
#else
#define lduw_p(p) lduw_le_p(p)
#define ldsw_p(p) ldsw_le_p(p)
#define ldl_p(p) ldl_le_p(p)
#define ldq_p(p) ldq_le_p(p)
#define ldfl_p(p) ldfl_le_p(p)
#define ldfq_p(p) ldfq_le_p(p)
#define stw_p(p, v) stw_le_p(p, v)
#define stl_p(p, v) stl_le_p(p, v)
#define stq_p(p, v) stq_le_p(p, v)
#define stfl_p(p, v) stfl_le_p(p, v)
#define stfq_p(p, v) stfq_le_p(p, v)
#endif

/* MMU memory access macros */

#if defined(CONFIG_USER_ONLY)
#include <assert.h>
#include "qemu-types.h"

/* On some host systems the guest address space is reserved on the host.
 * This allows the guest address space to be offset to a convenient location.
 */
#if defined(CONFIG_USE_GUEST_BASE)
extern unsigned long guest_base;
extern int have_guest_base;
extern unsigned long reserved_va;
#define GUEST_BASE guest_base
#define RESERVED_VA reserved_va
#else
#define GUEST_BASE 0ul
#define RESERVED_VA 0ul
#endif

/* All direct uses of g2h and h2g need to go away for usermode softmmu.  */
#define g2h(x) ((void *)((unsigned long)(x) + GUEST_BASE))

#if HOST_LONG_BITS <= TARGET_VIRT_ADDR_SPACE_BITS
#define h2g_valid(x) 1
#else
#define h2g_valid(x) ({ \
    unsigned long __guest = (unsigned long)(x) - GUEST_BASE; \
    __guest < (1ul << TARGET_VIRT_ADDR_SPACE_BITS); \
})
#endif

#define h2g(x) ({ \
    unsigned long __ret = (unsigned long)(x) - GUEST_BASE; \
    /* Check if given address fits target address space */ \
    assert(h2g_valid(x)); \
    (abi_ulong)__ret; \
})

#define saddr(x) g2h(x)
#define laddr(x) g2h(x)

#else /* !CONFIG_USER_ONLY */
/* NOTE: we use double casts if pointers and target_ulong have
   different sizes */
#define saddr(x) (uint8_t *)(long)(x)
#define laddr(x) (uint8_t *)(long)(x)
#endif

#define ldub_raw(p) ldub_p(laddr((p)))
#define ldsb_raw(p) ldsb_p(laddr((p)))
#define lduw_raw(p) lduw_p(laddr((p)))
#define ldsw_raw(p) ldsw_p(laddr((p)))
#define ldl_raw(p) ldl_p(laddr((p)))
#define ldq_raw(p) ldq_p(laddr((p)))
#define ldfl_raw(p) ldfl_p(laddr((p)))
#define ldfq_raw(p) ldfq_p(laddr((p)))
#define stb_raw(p, v) stb_p(saddr((p)), v)
#define stw_raw(p, v) stw_p(saddr((p)), v)
#define stl_raw(p, v) stl_p(saddr((p)), v)
#define stq_raw(p, v) stq_p(saddr((p)), v)
#define stfl_raw(p, v) stfl_p(saddr((p)), v)
#define stfq_raw(p, v) stfq_p(saddr((p)), v)


#if defined(CONFIG_USER_ONLY)

/* if user mode, no other memory access functions */
#define ldub(p) ldub_raw(p)
#define ldsb(p) ldsb_raw(p)
#define lduw(p) lduw_raw(p)
#define ldsw(p) ldsw_raw(p)
#define ldl(p) ldl_raw(p)
#define ldq(p) ldq_raw(p)
#define ldfl(p) ldfl_raw(p)
#define ldfq(p) ldfq_raw(p)
#define stb(p, v) stb_raw(p, v)
#define stw(p, v) stw_raw(p, v)
#define stl(p, v) stl_raw(p, v)
#define stq(p, v) stq_raw(p, v)
#define stfl(p, v) stfl_raw(p, v)
#define stfq(p, v) stfq_raw(p, v)

#define ldub_code(p) ldub_raw(p)
#define ldsb_code(p) ldsb_raw(p)
#define lduw_code(p) lduw_raw(p)
#define ldsw_code(p) ldsw_raw(p)
#define ldl_code(p) ldl_raw(p)
#define ldq_code(p) ldq_raw(p)

#define ldub_kernel(p) ldub_raw(p)
#define ldsb_kernel(p) ldsb_raw(p)
#define lduw_kernel(p) lduw_raw(p)
#define ldsw_kernel(p) ldsw_raw(p)
#define ldl_kernel(p) ldl_raw(p)
#define ldq_kernel(p) ldq_raw(p)
#define ldfl_kernel(p) ldfl_raw(p)
#define ldfq_kernel(p) ldfq_raw(p)
#define stb_kernel(p, v) stb_raw(p, v)
#define stw_kernel(p, v) stw_raw(p, v)
#define stl_kernel(p, v) stl_raw(p, v)
#define stq_kernel(p, v) stq_raw(p, v)
#define stfl_kernel(p, v) stfl_raw(p, v)
#define stfq_kernel(p, vt) stfq_raw(p, v)

#endif /* defined(CONFIG_USER_ONLY) */

/* page related stuff */

#define TARGET_PAGE_SIZE (1 << TARGET_PAGE_BITS)
#define TARGET_PAGE_MASK ~(TARGET_PAGE_SIZE - 1)
#define TARGET_PAGE_ALIGN(addr) (((addr) + TARGET_PAGE_SIZE - 1) & TARGET_PAGE_MASK)

/* ??? These should be the larger of unsigned long and target_ulong.  */
extern unsigned long qemu_real_host_page_size;
extern unsigned long qemu_host_page_bits;
extern unsigned long qemu_host_page_size;
extern unsigned long qemu_host_page_mask;

#define HOST_PAGE_ALIGN(addr) (((addr) + qemu_host_page_size - 1) & qemu_host_page_mask)

/* same as PROT_xxx */
#define PAGE_READ      0x0001
#define PAGE_WRITE     0x0002
#define PAGE_EXEC      0x0004
#define PAGE_BITS      (PAGE_READ | PAGE_WRITE | PAGE_EXEC)
#define PAGE_VALID     0x0008
/* original state of the write flag (used when tracking self-modifying
   code */
#define PAGE_WRITE_ORG 0x0010
#if defined(CONFIG_BSD) && defined(CONFIG_USER_ONLY)
/* FIXME: Code that sets/uses this is broken and needs to go away.  */
#define PAGE_RESERVED  0x0020
#endif

#if defined(CONFIG_USER_ONLY)
void page_dump(FILE *f);

typedef int (*walk_memory_regions_fn)(void *, abi_ulong,
                                      abi_ulong, unsigned long);
int walk_memory_regions(void *, walk_memory_regions_fn);

int page_get_flags(target_ulong address);
void page_set_flags(target_ulong start, target_ulong end, int flags);
int page_check_range(target_ulong start, target_ulong len, int flags);
#endif

CPUState *cpu_copy(CPUState *env);
CPUState *qemu_get_cpu(int cpu);

void cpu_dump_state(CPUState *env, FILE *f,
                    int (*cpu_fprintf)(FILE *f, const char *fmt, ...),
                    int flags);
void cpu_dump_statistics (CPUState *env, FILE *f,
                          int (*cpu_fprintf)(FILE *f, const char *fmt, ...),
                          int flags);

void QEMU_NORETURN cpu_abort(CPUState *env, const char *fmt, ...)
    __attribute__ ((__format__ (__printf__, 2, 3)));
extern CPUState *first_cpu;
extern CPUState *cpu_single_env;

#define CPU_INTERRUPT_HARD   0x02 /* hardware interrupt pending */
#define CPU_INTERRUPT_EXITTB 0x04 /* exit the current TB (use for x86 a20 case) */
#define CPU_INTERRUPT_TIMER  0x08 /* internal timer exception pending */
#define CPU_INTERRUPT_FIQ    0x10 /* Fast interrupt pending.  */
#define CPU_INTERRUPT_HALT   0x20 /* CPU halt wanted */
#define CPU_INTERRUPT_SMI    0x40 /* (x86 only) SMI interrupt pending */
#define CPU_INTERRUPT_DEBUG  0x80 /* Debug event occured.  */
#define CPU_INTERRUPT_VIRQ   0x100 /* virtual interrupt pending.  */
#define CPU_INTERRUPT_NMI    0x200 /* NMI pending. */
#define CPU_INTERRUPT_INIT   0x400 /* INIT pending. */
#define CPU_INTERRUPT_SIPI   0x800 /* SIPI pending. */
#define CPU_INTERRUPT_MCE    0x1000 /* (x86 only) MCE pending. */

void cpu_interrupt(CPUState *s, int mask);
void cpu_reset_interrupt(CPUState *env, int mask);

void cpu_exit(CPUState *s);

int qemu_cpu_has_work(CPUState *env);

/* Breakpoint/watchpoint flags */
#define BP_MEM_READ           0x01
#define BP_MEM_WRITE          0x02
#define BP_MEM_ACCESS         (BP_MEM_READ | BP_MEM_WRITE)
#define BP_STOP_BEFORE_ACCESS 0x04
#define BP_WATCHPOINT_HIT     0x08
#define BP_GDB                0x10
#define BP_CPU                0x20

int cpu_breakpoint_insert(CPUState *env, target_ulong pc, int flags,
                          CPUBreakpoint **breakpoint);
int cpu_breakpoint_remove(CPUState *env, target_ulong pc, int flags);
void cpu_breakpoint_remove_by_ref(CPUState *env, CPUBreakpoint *breakpoint);
void cpu_breakpoint_remove_all(CPUState *env, int mask);
int cpu_watchpoint_insert(CPUState *env, target_ulong addr, target_ulong len,
                          int flags, CPUWatchpoint **watchpoint);
int cpu_watchpoint_remove(CPUState *env, target_ulong addr,
                          target_ulong len, int flags);
void cpu_watchpoint_remove_by_ref(CPUState *env, CPUWatchpoint *watchpoint);
void cpu_watchpoint_remove_all(CPUState *env, int mask);

#define SSTEP_ENABLE  0x1  /* Enable simulated HW single stepping */
#define SSTEP_NOIRQ   0x2  /* Do not use IRQ while single stepping */
#define SSTEP_NOTIMER 0x4  /* Do not Timers while single stepping */

void cpu_single_step(CPUState *env, int enabled);
void cpu_reset(CPUState *s);
int cpu_is_stopped(CPUState *env);
void run_on_cpu(CPUState *env, void (*func)(void *data), void *data);

#define CPU_LOG_TB_OUT_ASM (1 << 0)
#define CPU_LOG_TB_IN_ASM  (1 << 1)
#define CPU_LOG_TB_OP      (1 << 2)
#define CPU_LOG_TB_OP_OPT  (1 << 3)
#define CPU_LOG_INT        (1 << 4)
#define CPU_LOG_EXEC       (1 << 5)
#define CPU_LOG_PCALL      (1 << 6)
#define CPU_LOG_IOPORT     (1 << 7)
#define CPU_LOG_TB_CPU     (1 << 8)
#define CPU_LOG_RESET      (1 << 9)

/* define log items */
typedef struct CPULogItem {
    int mask;
    const char *name;
    const char *help;
} CPULogItem;

extern const CPULogItem cpu_log_items[];

void cpu_set_log(int log_flags);
void cpu_set_log_filename(const char *filename);
int cpu_str_to_log_mask(const char *str);

/* IO ports API */
#include "ioport.h"

/* Return the physical page corresponding to a virtual one. Use it
   only for debugging because no protection checks are done. Return -1
   if no page found. */
target_phys_addr_t cpu_get_phys_page_debug(CPUState *env, target_ulong addr);

/* memory API */

extern int phys_ram_fd;
extern uint8_t *phys_ram_dirty;
extern ram_addr_t ram_size;
extern ram_addr_t last_ram_offset;

/* physical memory access */

/* MMIO pages are identified by a combination of an IO device index and
   3 flags.  The ROMD code stores the page ram offset in iotlb entry, 
   so only a limited number of ids are avaiable.  */

#define IO_MEM_NB_ENTRIES  (1 << (TARGET_PAGE_BITS  - IO_MEM_SHIFT))

/* Flags stored in the low bits of the TLB virtual address.  These are
   defined so that fast path ram access is all zeros.  */
/* Zero if TLB entry is valid.  */
#define TLB_INVALID_MASK   (1 << 3)
/* Set if TLB entry references a clean RAM page.  The iotlb entry will
   contain the page physical address.  */
#define TLB_NOTDIRTY    (1 << 4)
/* Set if TLB entry is an IO callback.  */
#define TLB_MMIO        (1 << 5)

#define VGA_DIRTY_FLAG       0x01
#define CODE_DIRTY_FLAG      0x02
#define MIGRATION_DIRTY_FLAG 0x08

/* read dirty bit (return 0 or 1) */
static inline int cpu_physical_memory_is_dirty(ram_addr_t addr)
{
    return phys_ram_dirty[addr >> TARGET_PAGE_BITS] == 0xff;
}

static inline int cpu_physical_memory_get_dirty(ram_addr_t addr,
                                                int dirty_flags)
{
    return phys_ram_dirty[addr >> TARGET_PAGE_BITS] & dirty_flags;
}

static inline void cpu_physical_memory_set_dirty(ram_addr_t addr)
{
    phys_ram_dirty[addr >> TARGET_PAGE_BITS] = 0xff;
}

void cpu_physical_memory_reset_dirty(ram_addr_t start, ram_addr_t end,
                                     int dirty_flags);
void cpu_tlb_update_dirty(CPUState *env);

int cpu_physical_memory_set_dirty_tracking(int enable);

int cpu_physical_memory_get_dirty_tracking(void);

int cpu_physical_sync_dirty_bitmap(target_phys_addr_t start_addr,
                                   target_phys_addr_t end_addr);

void dump_exec_info(FILE *f,
                    int (*cpu_fprintf)(FILE *f, const char *fmt, ...));

/* Coalesced MMIO regions are areas where write operations can be reordered.
 * This usually implies that write operations are side-effect free.  This allows
 * batching which can make a major impact on performance when using
 * virtualization.
 */
void qemu_register_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size);

void qemu_unregister_coalesced_mmio(target_phys_addr_t addr, ram_addr_t size);

void qemu_flush_coalesced_mmio_buffer(void);


/* profiling */
#ifdef CONFIG_PROFILER
static inline int64_t profile_getclock(void)
{
    return cpu_get_real_ticks();
}

extern int64_t qemu_time, qemu_time_start;
extern int64_t tlb_flush_time;
extern int64_t dev_time;
#endif

int cpu_memory_rw_debug(CPUState *env, target_ulong addr,
                        uint8_t *buf, int len, int is_write);

void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
                        uint64_t mcg_status, uint64_t addr, uint64_t misc);

#endif /* CPU_ALL_H */