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
|
/*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Copyright (C) 2012 Regents of the University of California
* Copyright (C) 2017 SiFive
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#ifndef _ASM_RISCV_ATOMIC_H
#define _ASM_RISCV_ATOMIC_H
#ifdef CONFIG_GENERIC_ATOMIC64
# include <asm-generic/atomic64.h>
#else
# if (__riscv_xlen < 64)
# error "64-bit atomics require XLEN to be at least 64"
# endif
#endif
#include <asm/cmpxchg.h>
#include <asm/barrier.h>
#define ATOMIC_INIT(i) { (i) }
#define __atomic_op_acquire(op, args...) \
({ \
typeof(op##_relaxed(args)) __ret = op##_relaxed(args); \
__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory"); \
__ret; \
})
#define __atomic_op_release(op, args...) \
({ \
__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); \
op##_relaxed(args); \
})
static __always_inline int atomic_read(const atomic_t *v)
{
return READ_ONCE(v->counter);
}
static __always_inline void atomic_set(atomic_t *v, int i)
{
WRITE_ONCE(v->counter, i);
}
#ifndef CONFIG_GENERIC_ATOMIC64
#define ATOMIC64_INIT(i) { (i) }
static __always_inline long atomic64_read(const atomic64_t *v)
{
return READ_ONCE(v->counter);
}
static __always_inline void atomic64_set(atomic64_t *v, long i)
{
WRITE_ONCE(v->counter, i);
}
#endif
/*
* First, the atomic ops that have no ordering constraints and therefor don't
* have the AQ or RL bits set. These don't return anything, so there's only
* one version to worry about.
*/
#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \
static __always_inline \
void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
{ \
__asm__ __volatile__ ( \
" amo" #asm_op "." #asm_type " zero, %1, %0" \
: "+A" (v->counter) \
: "r" (I) \
: "memory"); \
} \
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, I) \
ATOMIC_OP (op, asm_op, I, w, int, )
#else
#define ATOMIC_OPS(op, asm_op, I) \
ATOMIC_OP (op, asm_op, I, w, int, ) \
ATOMIC_OP (op, asm_op, I, d, long, 64)
#endif
ATOMIC_OPS(add, add, i)
ATOMIC_OPS(sub, add, -i)
ATOMIC_OPS(and, and, i)
ATOMIC_OPS( or, or, i)
ATOMIC_OPS(xor, xor, i)
#undef ATOMIC_OP
#undef ATOMIC_OPS
/*
* Atomic ops that have ordered, relaxed, acquire, and release variants.
* There's two flavors of these: the arithmatic ops have both fetch and return
* versions, while the logical ops only have fetch versions.
*/
#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \
static __always_inline \
c_type atomic##prefix##_fetch_##op##_relaxed(c_type i, \
atomic##prefix##_t *v) \
{ \
register c_type ret; \
__asm__ __volatile__ ( \
" amo" #asm_op "." #asm_type " %1, %2, %0" \
: "+A" (v->counter), "=r" (ret) \
: "r" (I) \
: "memory"); \
return ret; \
} \
static __always_inline \
c_type atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v) \
{ \
register c_type ret; \
__asm__ __volatile__ ( \
" amo" #asm_op "." #asm_type ".aqrl %1, %2, %0" \
: "+A" (v->counter), "=r" (ret) \
: "r" (I) \
: "memory"); \
return ret; \
}
#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix) \
static __always_inline \
c_type atomic##prefix##_##op##_return_relaxed(c_type i, \
atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I; \
} \
static __always_inline \
c_type atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##op(i, v) c_op I; \
}
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I) \
ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I) \
ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, ) \
ATOMIC_FETCH_OP( op, asm_op, I, d, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, long, 64)
#endif
ATOMIC_OPS(add, add, +, i)
ATOMIC_OPS(sub, add, +, -i)
#define atomic_add_return_relaxed atomic_add_return_relaxed
#define atomic_sub_return_relaxed atomic_sub_return_relaxed
#define atomic_add_return atomic_add_return
#define atomic_sub_return atomic_sub_return
#define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
#define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
#define atomic_fetch_add atomic_fetch_add
#define atomic_fetch_sub atomic_fetch_sub
#ifndef CONFIG_GENERIC_ATOMIC64
#define atomic64_add_return_relaxed atomic64_add_return_relaxed
#define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
#define atomic64_add_return atomic64_add_return
#define atomic64_sub_return atomic64_sub_return
#define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
#define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
#define atomic64_fetch_add atomic64_fetch_add
#define atomic64_fetch_sub atomic64_fetch_sub
#endif
#undef ATOMIC_OPS
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, I) \
ATOMIC_FETCH_OP(op, asm_op, I, w, int, )
#else
#define ATOMIC_OPS(op, asm_op, I) \
ATOMIC_FETCH_OP(op, asm_op, I, w, int, ) \
ATOMIC_FETCH_OP(op, asm_op, I, d, long, 64)
#endif
ATOMIC_OPS(and, and, i)
ATOMIC_OPS( or, or, i)
ATOMIC_OPS(xor, xor, i)
#define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
#define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
#define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
#define atomic_fetch_and atomic_fetch_and
#define atomic_fetch_or atomic_fetch_or
#define atomic_fetch_xor atomic_fetch_xor
#ifndef CONFIG_GENERIC_ATOMIC64
#define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
#define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
#define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
#define atomic64_fetch_and atomic64_fetch_and
#define atomic64_fetch_or atomic64_fetch_or
#define atomic64_fetch_xor atomic64_fetch_xor
#endif
#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
/*
* The extra atomic operations that are constructed from one of the core
* AMO-based operations above (aside from sub, which is easier to fit above).
* These are required to perform a full barrier, but they're OK this way
* because atomic_*_return is also required to perform a full barrier.
*
*/
#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix) \
static __always_inline \
bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \
{ \
return atomic##prefix##_##func_op##_return(i, v) comp_op I; \
}
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, func_op, comp_op, I) \
ATOMIC_OP(op, func_op, comp_op, I, int, )
#else
#define ATOMIC_OPS(op, func_op, comp_op, I) \
ATOMIC_OP(op, func_op, comp_op, I, int, ) \
ATOMIC_OP(op, func_op, comp_op, I, long, 64)
#endif
ATOMIC_OPS(add_and_test, add, ==, 0)
ATOMIC_OPS(sub_and_test, sub, ==, 0)
ATOMIC_OPS(add_negative, add, <, 0)
#undef ATOMIC_OP
#undef ATOMIC_OPS
#define ATOMIC_OP(op, func_op, I, c_type, prefix) \
static __always_inline \
void atomic##prefix##_##op(atomic##prefix##_t *v) \
{ \
atomic##prefix##_##func_op(I, v); \
}
#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix) \
static __always_inline \
c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##func_op##_relaxed(I, v); \
} \
static __always_inline \
c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##func_op(I, v); \
}
#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix) \
static __always_inline \
c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##op##_relaxed(v) c_op I; \
} \
static __always_inline \
c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_fetch_##op(v) c_op I; \
}
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS(op, asm_op, c_op, I) \
ATOMIC_OP( op, asm_op, I, int, ) \
ATOMIC_FETCH_OP( op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, )
#else
#define ATOMIC_OPS(op, asm_op, c_op, I) \
ATOMIC_OP( op, asm_op, I, int, ) \
ATOMIC_FETCH_OP( op, asm_op, I, int, ) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, int, ) \
ATOMIC_OP( op, asm_op, I, long, 64) \
ATOMIC_FETCH_OP( op, asm_op, I, long, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
#endif
ATOMIC_OPS(inc, add, +, 1)
ATOMIC_OPS(dec, add, +, -1)
#define atomic_inc_return_relaxed atomic_inc_return_relaxed
#define atomic_dec_return_relaxed atomic_dec_return_relaxed
#define atomic_inc_return atomic_inc_return
#define atomic_dec_return atomic_dec_return
#define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed
#define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed
#define atomic_fetch_inc atomic_fetch_inc
#define atomic_fetch_dec atomic_fetch_dec
#ifndef CONFIG_GENERIC_ATOMIC64
#define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
#define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
#define atomic64_inc_return atomic64_inc_return
#define atomic64_dec_return atomic64_dec_return
#define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed
#define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed
#define atomic64_fetch_inc atomic64_fetch_inc
#define atomic64_fetch_dec atomic64_fetch_dec
#endif
#undef ATOMIC_OPS
#undef ATOMIC_OP
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
#define ATOMIC_OP(op, func_op, comp_op, I, prefix) \
static __always_inline \
bool atomic##prefix##_##op(atomic##prefix##_t *v) \
{ \
return atomic##prefix##_##func_op##_return(v) comp_op I; \
}
ATOMIC_OP(inc_and_test, inc, ==, 0, )
ATOMIC_OP(dec_and_test, dec, ==, 0, )
#ifndef CONFIG_GENERIC_ATOMIC64
ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
#endif
#undef ATOMIC_OP
/* This is required to provide a full barrier on success. */
static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
int prev, rc;
__asm__ __volatile__ (
"0: lr.w %[p], %[c]\n"
" beq %[p], %[u], 1f\n"
" add %[rc], %[p], %[a]\n"
" sc.w.rl %[rc], %[rc], %[c]\n"
" bnez %[rc], 0b\n"
" fence rw, rw\n"
"1:\n"
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
: [a]"r" (a), [u]"r" (u)
: "memory");
return prev;
}
#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
{
long prev, rc;
__asm__ __volatile__ (
"0: lr.d %[p], %[c]\n"
" beq %[p], %[u], 1f\n"
" add %[rc], %[p], %[a]\n"
" sc.d.rl %[rc], %[rc], %[c]\n"
" bnez %[rc], 0b\n"
" fence rw, rw\n"
"1:\n"
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
: [a]"r" (a), [u]"r" (u)
: "memory");
return prev;
}
static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
{
return __atomic64_add_unless(v, a, u) != u;
}
#endif
/*
* atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
* {cmp,}xchg and the operations that return, so they need a full barrier.
*/
#define ATOMIC_OP(c_t, prefix, size) \
static __always_inline \
c_t atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_relaxed(&(v->counter), n, size); \
} \
static __always_inline \
c_t atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_acquire(&(v->counter), n, size); \
} \
static __always_inline \
c_t atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_release(&(v->counter), n, size); \
} \
static __always_inline \
c_t atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg(&(v->counter), n, size); \
} \
static __always_inline \
c_t atomic##prefix##_cmpxchg_relaxed(atomic##prefix##_t *v, \
c_t o, c_t n) \
{ \
return __cmpxchg_relaxed(&(v->counter), o, n, size); \
} \
static __always_inline \
c_t atomic##prefix##_cmpxchg_acquire(atomic##prefix##_t *v, \
c_t o, c_t n) \
{ \
return __cmpxchg_acquire(&(v->counter), o, n, size); \
} \
static __always_inline \
c_t atomic##prefix##_cmpxchg_release(atomic##prefix##_t *v, \
c_t o, c_t n) \
{ \
return __cmpxchg_release(&(v->counter), o, n, size); \
} \
static __always_inline \
c_t atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n) \
{ \
return __cmpxchg(&(v->counter), o, n, size); \
}
#ifdef CONFIG_GENERIC_ATOMIC64
#define ATOMIC_OPS() \
ATOMIC_OP( int, , 4)
#else
#define ATOMIC_OPS() \
ATOMIC_OP( int, , 4) \
ATOMIC_OP(long, 64, 8)
#endif
ATOMIC_OPS()
#undef ATOMIC_OPS
#undef ATOMIC_OP
static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
{
int prev, rc;
__asm__ __volatile__ (
"0: lr.w %[p], %[c]\n"
" sub %[rc], %[p], %[o]\n"
" bltz %[rc], 1f\n"
" sc.w.rl %[rc], %[rc], %[c]\n"
" bnez %[rc], 0b\n"
" fence rw, rw\n"
"1:\n"
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
: [o]"r" (offset)
: "memory");
return prev - offset;
}
#define atomic_dec_if_positive(v) atomic_sub_if_positive(v, 1)
#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline long atomic64_sub_if_positive(atomic64_t *v, int offset)
{
long prev, rc;
__asm__ __volatile__ (
"0: lr.d %[p], %[c]\n"
" sub %[rc], %[p], %[o]\n"
" bltz %[rc], 1f\n"
" sc.d.rl %[rc], %[rc], %[c]\n"
" bnez %[rc], 0b\n"
" fence rw, rw\n"
"1:\n"
: [p]"=&r" (prev), [rc]"=&r" (rc), [c]"+A" (v->counter)
: [o]"r" (offset)
: "memory");
return prev - offset;
}
#define atomic64_dec_if_positive(v) atomic64_sub_if_positive(v, 1)
#endif
#endif /* _ASM_RISCV_ATOMIC_H */
|