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
|
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Based on arch/arm/include/asm/atomic.h
*
* Copyright (C) 1996 Russell King.
* Copyright (C) 2002 Deep Blue Solutions Ltd.
* Copyright (C) 2012 ARM Ltd.
*/
#ifndef __ASM_ATOMIC_LSE_H
#define __ASM_ATOMIC_LSE_H
#ifndef __ARM64_IN_ATOMIC_IMPL
#error "please don't include this file directly"
#endif
#define __LL_SC_ATOMIC(op) __LL_SC_CALL(arch_atomic_##op)
#define ATOMIC_OP(op, asm_op) \
static inline void arch_atomic_##op(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC(op), \
" " #asm_op " %w[i], %[v]\n") \
: [i] "+r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS); \
}
ATOMIC_OP(andnot, stclr)
ATOMIC_OP(or, stset)
ATOMIC_OP(xor, steor)
ATOMIC_OP(add, stadd)
#undef ATOMIC_OP
#define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...) \
static inline int arch_atomic_fetch_##op##name(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC(fetch_##op##name), \
/* LSE atomics */ \
" " #asm_op #mb " %w[i], %w[i], %[v]") \
: [i] "+r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return w0; \
}
#define ATOMIC_FETCH_OPS(op, asm_op) \
ATOMIC_FETCH_OP(_relaxed, , op, asm_op) \
ATOMIC_FETCH_OP(_acquire, a, op, asm_op, "memory") \
ATOMIC_FETCH_OP(_release, l, op, asm_op, "memory") \
ATOMIC_FETCH_OP( , al, op, asm_op, "memory")
ATOMIC_FETCH_OPS(andnot, ldclr)
ATOMIC_FETCH_OPS(or, ldset)
ATOMIC_FETCH_OPS(xor, ldeor)
ATOMIC_FETCH_OPS(add, ldadd)
#undef ATOMIC_FETCH_OP
#undef ATOMIC_FETCH_OPS
#define ATOMIC_OP_ADD_RETURN(name, mb, cl...) \
static inline int arch_atomic_add_return##name(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC(add_return##name) \
__nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
: [i] "+r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return w0; \
}
ATOMIC_OP_ADD_RETURN(_relaxed, )
ATOMIC_OP_ADD_RETURN(_acquire, a, "memory")
ATOMIC_OP_ADD_RETURN(_release, l, "memory")
ATOMIC_OP_ADD_RETURN( , al, "memory")
#undef ATOMIC_OP_ADD_RETURN
static inline void arch_atomic_and(int i, atomic_t *v)
{
register int w0 asm ("w0") = i;
register atomic_t *x1 asm ("x1") = v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
__LL_SC_ATOMIC(and)
__nops(1),
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
: [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
#define ATOMIC_FETCH_OP_AND(name, mb, cl...) \
static inline int arch_atomic_fetch_and##name(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC(fetch_and##name) \
__nops(1), \
/* LSE atomics */ \
" mvn %w[i], %w[i]\n" \
" ldclr" #mb " %w[i], %w[i], %[v]") \
: [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return w0; \
}
ATOMIC_FETCH_OP_AND(_relaxed, )
ATOMIC_FETCH_OP_AND(_acquire, a, "memory")
ATOMIC_FETCH_OP_AND(_release, l, "memory")
ATOMIC_FETCH_OP_AND( , al, "memory")
#undef ATOMIC_FETCH_OP_AND
static inline void arch_atomic_sub(int i, atomic_t *v)
{
register int w0 asm ("w0") = i;
register atomic_t *x1 asm ("x1") = v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
__LL_SC_ATOMIC(sub)
__nops(1),
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
: [i] "+&r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
#define ATOMIC_OP_SUB_RETURN(name, mb, cl...) \
static inline int arch_atomic_sub_return##name(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC(sub_return##name) \
__nops(2), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], w30, %[v]\n" \
" add %w[i], %w[i], w30") \
: [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS , ##cl); \
\
return w0; \
}
ATOMIC_OP_SUB_RETURN(_relaxed, )
ATOMIC_OP_SUB_RETURN(_acquire, a, "memory")
ATOMIC_OP_SUB_RETURN(_release, l, "memory")
ATOMIC_OP_SUB_RETURN( , al, "memory")
#undef ATOMIC_OP_SUB_RETURN
#define ATOMIC_FETCH_OP_SUB(name, mb, cl...) \
static inline int arch_atomic_fetch_sub##name(int i, atomic_t *v) \
{ \
register int w0 asm ("w0") = i; \
register atomic_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC(fetch_sub##name) \
__nops(1), \
/* LSE atomics */ \
" neg %w[i], %w[i]\n" \
" ldadd" #mb " %w[i], %w[i], %[v]") \
: [i] "+&r" (w0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return w0; \
}
ATOMIC_FETCH_OP_SUB(_relaxed, )
ATOMIC_FETCH_OP_SUB(_acquire, a, "memory")
ATOMIC_FETCH_OP_SUB(_release, l, "memory")
ATOMIC_FETCH_OP_SUB( , al, "memory")
#undef ATOMIC_FETCH_OP_SUB
#undef __LL_SC_ATOMIC
#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(arch_atomic64_##op)
#define ATOMIC64_OP(op, asm_op) \
static inline void arch_atomic64_##op(long i, atomic64_t *v) \
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op), \
" " #asm_op " %[i], %[v]\n") \
: [i] "+r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS); \
}
ATOMIC64_OP(andnot, stclr)
ATOMIC64_OP(or, stset)
ATOMIC64_OP(xor, steor)
ATOMIC64_OP(add, stadd)
#undef ATOMIC64_OP
#define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...) \
static inline long arch_atomic64_fetch_##op##name(long i, atomic64_t *v)\
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC64(fetch_##op##name), \
/* LSE atomics */ \
" " #asm_op #mb " %[i], %[i], %[v]") \
: [i] "+r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
#define ATOMIC64_FETCH_OPS(op, asm_op) \
ATOMIC64_FETCH_OP(_relaxed, , op, asm_op) \
ATOMIC64_FETCH_OP(_acquire, a, op, asm_op, "memory") \
ATOMIC64_FETCH_OP(_release, l, op, asm_op, "memory") \
ATOMIC64_FETCH_OP( , al, op, asm_op, "memory")
ATOMIC64_FETCH_OPS(andnot, ldclr)
ATOMIC64_FETCH_OPS(or, ldset)
ATOMIC64_FETCH_OPS(xor, ldeor)
ATOMIC64_FETCH_OPS(add, ldadd)
#undef ATOMIC64_FETCH_OP
#undef ATOMIC64_FETCH_OPS
#define ATOMIC64_OP_ADD_RETURN(name, mb, cl...) \
static inline long arch_atomic64_add_return##name(long i, atomic64_t *v)\
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC64(add_return##name) \
__nops(1), \
/* LSE atomics */ \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
: [i] "+r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
ATOMIC64_OP_ADD_RETURN(_relaxed, )
ATOMIC64_OP_ADD_RETURN(_acquire, a, "memory")
ATOMIC64_OP_ADD_RETURN(_release, l, "memory")
ATOMIC64_OP_ADD_RETURN( , al, "memory")
#undef ATOMIC64_OP_ADD_RETURN
static inline void arch_atomic64_and(long i, atomic64_t *v)
{
register long x0 asm ("x0") = i;
register atomic64_t *x1 asm ("x1") = v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
__LL_SC_ATOMIC64(and)
__nops(1),
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
: [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
#define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \
static inline long arch_atomic64_fetch_and##name(long i, atomic64_t *v) \
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC64(fetch_and##name) \
__nops(1), \
/* LSE atomics */ \
" mvn %[i], %[i]\n" \
" ldclr" #mb " %[i], %[i], %[v]") \
: [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
ATOMIC64_FETCH_OP_AND(_relaxed, )
ATOMIC64_FETCH_OP_AND(_acquire, a, "memory")
ATOMIC64_FETCH_OP_AND(_release, l, "memory")
ATOMIC64_FETCH_OP_AND( , al, "memory")
#undef ATOMIC64_FETCH_OP_AND
static inline void arch_atomic64_sub(long i, atomic64_t *v)
{
register long x0 asm ("x0") = i;
register atomic64_t *x1 asm ("x1") = v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
__LL_SC_ATOMIC64(sub)
__nops(1),
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
: [i] "+&r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: __LL_SC_CLOBBERS);
}
#define ATOMIC64_OP_SUB_RETURN(name, mb, cl...) \
static inline long arch_atomic64_sub_return##name(long i, atomic64_t *v)\
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC64(sub_return##name) \
__nops(2), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], x30, %[v]\n" \
" add %[i], %[i], x30") \
: [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
ATOMIC64_OP_SUB_RETURN(_relaxed, )
ATOMIC64_OP_SUB_RETURN(_acquire, a, "memory")
ATOMIC64_OP_SUB_RETURN(_release, l, "memory")
ATOMIC64_OP_SUB_RETURN( , al, "memory")
#undef ATOMIC64_OP_SUB_RETURN
#define ATOMIC64_FETCH_OP_SUB(name, mb, cl...) \
static inline long arch_atomic64_fetch_sub##name(long i, atomic64_t *v) \
{ \
register long x0 asm ("x0") = i; \
register atomic64_t *x1 asm ("x1") = v; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_ATOMIC64(fetch_sub##name) \
__nops(1), \
/* LSE atomics */ \
" neg %[i], %[i]\n" \
" ldadd" #mb " %[i], %[i], %[v]") \
: [i] "+&r" (x0), [v] "+Q" (v->counter) \
: "r" (x1) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
ATOMIC64_FETCH_OP_SUB(_relaxed, )
ATOMIC64_FETCH_OP_SUB(_acquire, a, "memory")
ATOMIC64_FETCH_OP_SUB(_release, l, "memory")
ATOMIC64_FETCH_OP_SUB( , al, "memory")
#undef ATOMIC64_FETCH_OP_SUB
static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
{
register long x0 asm ("x0") = (long)v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
__LL_SC_ATOMIC64(dec_if_positive)
__nops(6),
/* LSE atomics */
"1: ldr x30, %[v]\n"
" subs %[ret], x30, #1\n"
" b.lt 2f\n"
" casal x30, %[ret], %[v]\n"
" sub x30, x30, #1\n"
" sub x30, x30, %[ret]\n"
" cbnz x30, 1b\n"
"2:")
: [ret] "+&r" (x0), [v] "+Q" (v->counter)
:
: __LL_SC_CLOBBERS, "cc", "memory");
return x0;
}
#undef __LL_SC_ATOMIC64
#define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op)
#define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \
static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr, \
u##sz old, \
u##sz new) \
{ \
register unsigned long x0 asm ("x0") = (unsigned long)ptr; \
register u##sz x1 asm ("x1") = old; \
register u##sz x2 asm ("x2") = new; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_CMPXCHG(name##sz) \
__nops(2), \
/* LSE atomics */ \
" mov " #w "30, %" #w "[old]\n" \
" cas" #mb #sfx "\t" #w "30, %" #w "[new], %[v]\n" \
" mov %" #w "[ret], " #w "30") \
: [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr) \
: [old] "r" (x1), [new] "r" (x2) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
__CMPXCHG_CASE(w, b, , 8, )
__CMPXCHG_CASE(w, h, , 16, )
__CMPXCHG_CASE(w, , , 32, )
__CMPXCHG_CASE(x, , , 64, )
__CMPXCHG_CASE(w, b, acq_, 8, a, "memory")
__CMPXCHG_CASE(w, h, acq_, 16, a, "memory")
__CMPXCHG_CASE(w, , acq_, 32, a, "memory")
__CMPXCHG_CASE(x, , acq_, 64, a, "memory")
__CMPXCHG_CASE(w, b, rel_, 8, l, "memory")
__CMPXCHG_CASE(w, h, rel_, 16, l, "memory")
__CMPXCHG_CASE(w, , rel_, 32, l, "memory")
__CMPXCHG_CASE(x, , rel_, 64, l, "memory")
__CMPXCHG_CASE(w, b, mb_, 8, al, "memory")
__CMPXCHG_CASE(w, h, mb_, 16, al, "memory")
__CMPXCHG_CASE(w, , mb_, 32, al, "memory")
__CMPXCHG_CASE(x, , mb_, 64, al, "memory")
#undef __LL_SC_CMPXCHG
#undef __CMPXCHG_CASE
#define __LL_SC_CMPXCHG_DBL(op) __LL_SC_CALL(__cmpxchg_double##op)
#define __CMPXCHG_DBL(name, mb, cl...) \
static inline long __cmpxchg_double##name(unsigned long old1, \
unsigned long old2, \
unsigned long new1, \
unsigned long new2, \
volatile void *ptr) \
{ \
unsigned long oldval1 = old1; \
unsigned long oldval2 = old2; \
register unsigned long x0 asm ("x0") = old1; \
register unsigned long x1 asm ("x1") = old2; \
register unsigned long x2 asm ("x2") = new1; \
register unsigned long x3 asm ("x3") = new2; \
register unsigned long x4 asm ("x4") = (unsigned long)ptr; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
__LL_SC_CMPXCHG_DBL(name) \
__nops(3), \
/* LSE atomics */ \
" casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
" eor %[old1], %[old1], %[oldval1]\n" \
" eor %[old2], %[old2], %[oldval2]\n" \
" orr %[old1], %[old1], %[old2]") \
: [old1] "+&r" (x0), [old2] "+&r" (x1), \
[v] "+Q" (*(unsigned long *)ptr) \
: [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \
[oldval1] "r" (oldval1), [oldval2] "r" (oldval2) \
: __LL_SC_CLOBBERS, ##cl); \
\
return x0; \
}
__CMPXCHG_DBL( , )
__CMPXCHG_DBL(_mb, al, "memory")
#undef __LL_SC_CMPXCHG_DBL
#undef __CMPXCHG_DBL
#endif /* __ASM_ATOMIC_LSE_H */
|
