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
|
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Copyright (C) 2012 Regents of the University of California
* Copyright (C) 2017 SiFive
*/
#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_acquire_fence() \
__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
#define __atomic_release_fence() \
__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
static __always_inline int arch_atomic_read(const atomic_t *v)
{
return READ_ONCE(v->counter);
}
static __always_inline void arch_atomic_set(atomic_t *v, int i)
{
WRITE_ONCE(v->counter, i);
}
#ifndef CONFIG_GENERIC_ATOMIC64
#define ATOMIC64_INIT(i) { (i) }
static __always_inline s64 arch_atomic64_read(const atomic64_t *v)
{
return READ_ONCE(v->counter);
}
static __always_inline void arch_atomic64_set(atomic64_t *v, s64 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 arch_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, s64, 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 arch_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 arch_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 arch_atomic##prefix##_##op##_return_relaxed(c_type i, \
atomic##prefix##_t *v) \
{ \
return arch_atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I; \
} \
static __always_inline \
c_type arch_atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v) \
{ \
return arch_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, s64, 64) \
ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, s64, 64)
#endif
ATOMIC_OPS(add, add, +, i)
ATOMIC_OPS(sub, add, +, -i)
#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed
#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed
#define arch_atomic_add_return arch_atomic_add_return
#define arch_atomic_sub_return arch_atomic_sub_return
#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed
#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed
#define arch_atomic_fetch_add arch_atomic_fetch_add
#define arch_atomic_fetch_sub arch_atomic_fetch_sub
#ifndef CONFIG_GENERIC_ATOMIC64
#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed
#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed
#define arch_atomic64_add_return arch_atomic64_add_return
#define arch_atomic64_sub_return arch_atomic64_sub_return
#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed
#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed
#define arch_atomic64_fetch_add arch_atomic64_fetch_add
#define arch_atomic64_fetch_sub arch_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, s64, 64)
#endif
ATOMIC_OPS(and, and, i)
ATOMIC_OPS( or, or, i)
ATOMIC_OPS(xor, xor, i)
#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed
#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed
#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed
#define arch_atomic_fetch_and arch_atomic_fetch_and
#define arch_atomic_fetch_or arch_atomic_fetch_or
#define arch_atomic_fetch_xor arch_atomic_fetch_xor
#ifndef CONFIG_GENERIC_ATOMIC64
#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed
#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed
#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed
#define arch_atomic64_fetch_and arch_atomic64_fetch_and
#define arch_atomic64_fetch_or arch_atomic64_fetch_or
#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
#endif
#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP
#undef ATOMIC_OP_RETURN
/* This is required to provide a full barrier on success. */
static __always_inline int arch_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;
}
#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
s64 prev;
long 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;
}
#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
#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 arch_atomic##prefix##_xchg_relaxed(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_relaxed(&(v->counter), n, size); \
} \
static __always_inline \
c_t arch_atomic##prefix##_xchg_acquire(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_acquire(&(v->counter), n, size); \
} \
static __always_inline \
c_t arch_atomic##prefix##_xchg_release(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg_release(&(v->counter), n, size); \
} \
static __always_inline \
c_t arch_atomic##prefix##_xchg(atomic##prefix##_t *v, c_t n) \
{ \
return __xchg(&(v->counter), n, size); \
} \
static __always_inline \
c_t arch_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 arch_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 arch_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 arch_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(s64, 64, 8)
#endif
ATOMIC_OPS()
#define arch_atomic_xchg_relaxed arch_atomic_xchg_relaxed
#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire
#define arch_atomic_xchg_release arch_atomic_xchg_release
#define arch_atomic_xchg arch_atomic_xchg
#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg_relaxed
#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire
#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release
#define arch_atomic_cmpxchg arch_atomic_cmpxchg
#undef ATOMIC_OPS
#undef ATOMIC_OP
static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v)
{
int prev, rc;
__asm__ __volatile__ (
"0: lr.w %[p], %[c]\n"
" bltz %[p], 1f\n"
" addi %[rc], %[p], 1\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)
:
: "memory");
return !(prev < 0);
}
#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v)
{
int prev, rc;
__asm__ __volatile__ (
"0: lr.w %[p], %[c]\n"
" bgtz %[p], 1f\n"
" addi %[rc], %[p], -1\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)
:
: "memory");
return !(prev > 0);
}
#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
static __always_inline int arch_atomic_dec_if_positive(atomic_t *v)
{
int prev, rc;
__asm__ __volatile__ (
"0: lr.w %[p], %[c]\n"
" addi %[rc], %[p], -1\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)
:
: "memory");
return prev - 1;
}
#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
#ifndef CONFIG_GENERIC_ATOMIC64
static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v)
{
s64 prev;
long rc;
__asm__ __volatile__ (
"0: lr.d %[p], %[c]\n"
" bltz %[p], 1f\n"
" addi %[rc], %[p], 1\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)
:
: "memory");
return !(prev < 0);
}
#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative
static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v)
{
s64 prev;
long rc;
__asm__ __volatile__ (
"0: lr.d %[p], %[c]\n"
" bgtz %[p], 1f\n"
" addi %[rc], %[p], -1\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)
:
: "memory");
return !(prev > 0);
}
#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive
static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
{
s64 prev;
long rc;
__asm__ __volatile__ (
"0: lr.d %[p], %[c]\n"
" addi %[rc], %[p], -1\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)
:
: "memory");
return prev - 1;
}
#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
#endif
#endif /* _ASM_RISCV_ATOMIC_H */
|
