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
|
#ifndef BSWAP_H
#define BSWAP_H
#undef bswap16
#define bswap16(_x) __builtin_bswap16(_x)
#undef bswap32
#define bswap32(_x) __builtin_bswap32(_x)
#undef bswap64
#define bswap64(_x) __builtin_bswap64(_x)
static inline uint32_t bswap24(uint32_t x)
{
return (((x & 0x000000ffU) << 16) |
((x & 0x0000ff00U) << 0) |
((x & 0x00ff0000U) >> 16));
}
static inline void bswap16s(uint16_t *s)
{
*s = __builtin_bswap16(*s);
}
static inline void bswap24s(uint32_t *s)
{
*s = bswap24(*s & 0x00ffffffU);
}
static inline void bswap32s(uint32_t *s)
{
*s = __builtin_bswap32(*s);
}
static inline void bswap64s(uint64_t *s)
{
*s = __builtin_bswap64(*s);
}
#if HOST_BIG_ENDIAN
#define be_bswap(v, size) (v)
#define le_bswap(v, size) glue(__builtin_bswap, size)(v)
#define be_bswap24(v) (v)
#define le_bswap24(v) bswap24(v)
#define be_bswaps(v, size)
#define le_bswaps(p, size) \
do { *p = glue(__builtin_bswap, size)(*p); } while (0)
#else
#define le_bswap(v, size) (v)
#define be_bswap24(v) bswap24(v)
#define le_bswap24(v) (v)
#define be_bswap(v, size) glue(__builtin_bswap, size)(v)
#define le_bswaps(v, size)
#define be_bswaps(p, size) \
do { *p = glue(__builtin_bswap, size)(*p); } while (0)
#endif
/**
* Endianness conversion functions between host cpu and specified endianness.
* (We list the complete set of prototypes produced by the macros below
* to assist people who search the headers to find their definitions.)
*
* uint16_t le16_to_cpu(uint16_t v);
* uint32_t le32_to_cpu(uint32_t v);
* uint64_t le64_to_cpu(uint64_t v);
* uint16_t be16_to_cpu(uint16_t v);
* uint32_t be32_to_cpu(uint32_t v);
* uint64_t be64_to_cpu(uint64_t v);
*
* Convert the value @v from the specified format to the native
* endianness of the host CPU by byteswapping if necessary, and
* return the converted value.
*
* uint16_t cpu_to_le16(uint16_t v);
* uint32_t cpu_to_le32(uint32_t v);
* uint64_t cpu_to_le64(uint64_t v);
* uint16_t cpu_to_be16(uint16_t v);
* uint32_t cpu_to_be32(uint32_t v);
* uint64_t cpu_to_be64(uint64_t v);
*
* Convert the value @v from the native endianness of the host CPU to
* the specified format by byteswapping if necessary, and return
* the converted value.
*
* void le16_to_cpus(uint16_t *v);
* void le32_to_cpus(uint32_t *v);
* void le64_to_cpus(uint64_t *v);
* void be16_to_cpus(uint16_t *v);
* void be32_to_cpus(uint32_t *v);
* void be64_to_cpus(uint64_t *v);
*
* Do an in-place conversion of the value pointed to by @v from the
* specified format to the native endianness of the host CPU.
*
* void cpu_to_le16s(uint16_t *v);
* void cpu_to_le32s(uint32_t *v);
* void cpu_to_le64s(uint64_t *v);
* void cpu_to_be16s(uint16_t *v);
* void cpu_to_be32s(uint32_t *v);
* void cpu_to_be64s(uint64_t *v);
*
* Do an in-place conversion of the value pointed to by @v from the
* native endianness of the host CPU to the specified format.
*
* Both X_to_cpu() and cpu_to_X() perform the same operation; you
* should use whichever one is better documenting of the function your
* code is performing.
*
* Do not use these functions for conversion of values which are in guest
* memory, since the data may not be sufficiently aligned for the host CPU's
* load and store instructions. Instead you should use the ld*_p() and
* st*_p() functions, which perform loads and stores of data of any
* required size and endianness and handle possible misalignment.
*/
#define CPU_CONVERT(endian, size, type)\
static inline type endian ## size ## _to_cpu(type v)\
{\
return glue(endian, _bswap)(v, size);\
}\
\
static inline type cpu_to_ ## endian ## size(type v)\
{\
return glue(endian, _bswap)(v, size);\
}\
\
static inline void endian ## size ## _to_cpus(type *p)\
{\
glue(endian, _bswaps)(p, size);\
}\
\
static inline void cpu_to_ ## endian ## size ## s(type *p)\
{\
glue(endian, _bswaps)(p, size);\
}
CPU_CONVERT(be, 16, uint16_t)
CPU_CONVERT(be, 32, uint32_t)
CPU_CONVERT(be, 64, uint64_t)
CPU_CONVERT(le, 16, uint16_t)
CPU_CONVERT(le, 32, uint32_t)
CPU_CONVERT(le, 64, uint64_t)
#undef CPU_CONVERT
/*
* Same as cpu_to_le{16,32,64}, except that gcc will figure the result is
* a compile-time constant if you pass in a constant. So this can be
* used to initialize static variables.
*/
#if HOST_BIG_ENDIAN
# define const_le64(_x) \
((((_x) & 0x00000000000000ffULL) << 56) | \
(((_x) & 0x000000000000ff00ULL) << 40) | \
(((_x) & 0x0000000000ff0000ULL) << 24) | \
(((_x) & 0x00000000ff000000ULL) << 8) | \
(((_x) & 0x000000ff00000000ULL) >> 8) | \
(((_x) & 0x0000ff0000000000ULL) >> 24) | \
(((_x) & 0x00ff000000000000ULL) >> 40) | \
(((_x) & 0xff00000000000000ULL) >> 56))
# define const_le32(_x) \
((((_x) & 0x000000ffU) << 24) | \
(((_x) & 0x0000ff00U) << 8) | \
(((_x) & 0x00ff0000U) >> 8) | \
(((_x) & 0xff000000U) >> 24))
# define const_le16(_x) \
((((_x) & 0x00ff) << 8) | \
(((_x) & 0xff00) >> 8))
#else
# define const_le64(_x) (_x)
# define const_le32(_x) (_x)
# define const_le16(_x) (_x)
#endif
/* unaligned/endian-independent pointer access */
/*
* the generic syntax is:
*
* load: ld{type}{sign}{size}_{endian}_p(ptr)
*
* store: st{type}{size}_{endian}_p(ptr, val)
*
* Note there are small differences with the softmmu access API!
*
* type is:
* (empty): integer access
* f : float access
*
* sign is:
* (empty): for 32 or 64 bit sizes (including floats and doubles)
* u : unsigned
* s : signed
*
* size is:
* b: 8 bits
* w: 16 bits
* 24: 24 bits
* l: 32 bits
* q: 64 bits
*
* endian is:
* he : host endian
* be : big endian
* le : little endian
* te : target endian
* (except for byte accesses, which have no endian infix).
*
* The target endian accessors are obviously only available to source
* files which are built per-target; they are defined in cpu-all.h.
*
* In all cases these functions take a host pointer.
* For accessors that take a guest address rather than a
* host address, see the cpu_{ld,st}_* accessors defined in
* cpu_ldst.h.
*
* For cases where the size to be used is not fixed at compile time,
* there are
* stn_{endian}_p(ptr, sz, val)
* which stores @val to @ptr as an @endian-order number @sz bytes in size
* and
* ldn_{endian}_p(ptr, sz)
* which loads @sz bytes from @ptr as an unsigned @endian-order number
* and returns it in a uint64_t.
*/
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, uint8_t v)
{
*(uint8_t *)ptr = v;
}
/*
* Any compiler worth its salt will turn these memcpy into native unaligned
* operations. Thus we don't need to play games with packed attributes, or
* inline byte-by-byte stores.
* Some compilation environments (eg some fortify-source implementations)
* may intercept memcpy() in a way that defeats the compiler optimization,
* though, so we use __builtin_memcpy() to give ourselves the best chance
* of good performance.
*/
static inline int lduw_he_p(const void *ptr)
{
uint16_t r;
__builtin_memcpy(&r, ptr, sizeof(r));
return r;
}
static inline int ldsw_he_p(const void *ptr)
{
int16_t r;
__builtin_memcpy(&r, ptr, sizeof(r));
return r;
}
static inline void stw_he_p(void *ptr, uint16_t v)
{
__builtin_memcpy(ptr, &v, sizeof(v));
}
static inline void st24_he_p(void *ptr, uint32_t v)
{
__builtin_memcpy(ptr, &v, 3);
}
static inline int ldl_he_p(const void *ptr)
{
int32_t r;
__builtin_memcpy(&r, ptr, sizeof(r));
return r;
}
static inline void stl_he_p(void *ptr, uint32_t v)
{
__builtin_memcpy(ptr, &v, sizeof(v));
}
static inline uint64_t ldq_he_p(const void *ptr)
{
uint64_t r;
__builtin_memcpy(&r, ptr, sizeof(r));
return r;
}
static inline void stq_he_p(void *ptr, uint64_t v)
{
__builtin_memcpy(ptr, &v, sizeof(v));
}
static inline int lduw_le_p(const void *ptr)
{
return (uint16_t)le_bswap(lduw_he_p(ptr), 16);
}
static inline int ldsw_le_p(const void *ptr)
{
return (int16_t)le_bswap(lduw_he_p(ptr), 16);
}
static inline int ldl_le_p(const void *ptr)
{
return le_bswap(ldl_he_p(ptr), 32);
}
static inline uint64_t ldq_le_p(const void *ptr)
{
return le_bswap(ldq_he_p(ptr), 64);
}
static inline void stw_le_p(void *ptr, uint16_t v)
{
stw_he_p(ptr, le_bswap(v, 16));
}
static inline void st24_le_p(void *ptr, uint32_t v)
{
st24_he_p(ptr, le_bswap24(v));
}
static inline void stl_le_p(void *ptr, uint32_t v)
{
stl_he_p(ptr, le_bswap(v, 32));
}
static inline void stq_le_p(void *ptr, uint64_t v)
{
stq_he_p(ptr, le_bswap(v, 64));
}
static inline int lduw_be_p(const void *ptr)
{
return (uint16_t)be_bswap(lduw_he_p(ptr), 16);
}
static inline int ldsw_be_p(const void *ptr)
{
return (int16_t)be_bswap(lduw_he_p(ptr), 16);
}
static inline int ldl_be_p(const void *ptr)
{
return be_bswap(ldl_he_p(ptr), 32);
}
static inline uint64_t ldq_be_p(const void *ptr)
{
return be_bswap(ldq_he_p(ptr), 64);
}
static inline void stw_be_p(void *ptr, uint16_t v)
{
stw_he_p(ptr, be_bswap(v, 16));
}
static inline void st24_be_p(void *ptr, uint32_t v)
{
st24_he_p(ptr, be_bswap24(v));
}
static inline void stl_be_p(void *ptr, uint32_t v)
{
stl_he_p(ptr, be_bswap(v, 32));
}
static inline void stq_be_p(void *ptr, uint64_t v)
{
stq_he_p(ptr, be_bswap(v, 64));
}
static inline unsigned long leul_to_cpu(unsigned long v)
{
#if HOST_LONG_BITS == 32
return le_bswap(v, 32);
#elif HOST_LONG_BITS == 64
return le_bswap(v, 64);
#else
# error Unknown sizeof long
#endif
}
/* Store v to p as a sz byte value in host order */
#define DO_STN_LDN_P(END) \
static inline void stn_## END ## _p(void *ptr, int sz, uint64_t v) \
{ \
switch (sz) { \
case 1: \
stb_p(ptr, v); \
break; \
case 2: \
stw_ ## END ## _p(ptr, v); \
break; \
case 4: \
stl_ ## END ## _p(ptr, v); \
break; \
case 8: \
stq_ ## END ## _p(ptr, v); \
break; \
default: \
g_assert_not_reached(); \
} \
} \
static inline uint64_t ldn_## END ## _p(const void *ptr, int sz) \
{ \
switch (sz) { \
case 1: \
return ldub_p(ptr); \
case 2: \
return lduw_ ## END ## _p(ptr); \
case 4: \
return (uint32_t)ldl_ ## END ## _p(ptr); \
case 8: \
return ldq_ ## END ## _p(ptr); \
default: \
g_assert_not_reached(); \
} \
}
DO_STN_LDN_P(he)
DO_STN_LDN_P(le)
DO_STN_LDN_P(be)
#undef DO_STN_LDN_P
#undef le_bswap
#undef be_bswap
#undef le_bswaps
#undef be_bswaps
#endif /* BSWAP_H */
|