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
|
/*
* 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.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
* This program 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#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(atomic_##op)
static inline void atomic_andnot(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(andnot),
" stclr %w[i], %[v]\n")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic_or(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(or),
" stset %w[i], %[v]\n")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic_xor(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(xor),
" steor %w[i], %[v]\n")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic_add(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(add),
" stadd %w[i], %[v]\n")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline int atomic_add_return(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 */
" nop\n"
__LL_SC_ATOMIC(add_return),
/* LSE atomics */
" ldaddal %w[i], w30, %[v]\n"
" add %w[i], %w[i], w30")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30", "memory");
return w0;
}
static inline void 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 */
" nop\n"
__LL_SC_ATOMIC(and),
/* LSE atomics */
" mvn %w[i], %w[i]\n"
" stclr %w[i], %[v]")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void 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 */
" nop\n"
__LL_SC_ATOMIC(sub),
/* LSE atomics */
" neg %w[i], %w[i]\n"
" stadd %w[i], %[v]")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline int atomic_sub_return(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 */
" nop\n"
__LL_SC_ATOMIC(sub_return)
" nop",
/* LSE atomics */
" neg %w[i], %w[i]\n"
" ldaddal %w[i], w30, %[v]\n"
" add %w[i], %w[i], w30")
: [i] "+r" (w0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30", "memory");
return w0;
}
#undef __LL_SC_ATOMIC
#define __LL_SC_ATOMIC64(op) __LL_SC_CALL(atomic64_##op)
static inline void atomic64_andnot(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(andnot),
" stclr %[i], %[v]\n")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic64_or(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(or),
" stset %[i], %[v]\n")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic64_xor(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(xor),
" steor %[i], %[v]\n")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void atomic64_add(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(add),
" stadd %[i], %[v]\n")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline long atomic64_add_return(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 */
" nop\n"
__LL_SC_ATOMIC64(add_return),
/* LSE atomics */
" ldaddal %[i], x30, %[v]\n"
" add %[i], %[i], x30")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30", "memory");
return x0;
}
static inline void 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 */
" nop\n"
__LL_SC_ATOMIC64(and),
/* LSE atomics */
" mvn %[i], %[i]\n"
" stclr %[i], %[v]")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline void 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 */
" nop\n"
__LL_SC_ATOMIC64(sub),
/* LSE atomics */
" neg %[i], %[i]\n"
" stadd %[i], %[v]")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30");
}
static inline long atomic64_sub_return(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 */
" nop\n"
__LL_SC_ATOMIC64(sub_return)
" nop",
/* LSE atomics */
" neg %[i], %[i]\n"
" ldaddal %[i], x30, %[v]\n"
" add %[i], %[i], x30")
: [i] "+r" (x0), [v] "+Q" (v->counter)
: "r" (x1)
: "x30", "memory");
return x0;
}
static inline long atomic64_dec_if_positive(atomic64_t *v)
{
register long x0 asm ("x0") = (long)v;
asm volatile(ARM64_LSE_ATOMIC_INSN(
/* LL/SC */
" nop\n"
__LL_SC_ATOMIC64(dec_if_positive)
" nop\n"
" nop\n"
" nop\n"
" nop\n"
" nop",
/* 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)
:
: "x30", "cc", "memory");
return x0;
}
#undef __LL_SC_ATOMIC64
#define __LL_SC_CMPXCHG(op) __LL_SC_CALL(__cmpxchg_case_##op)
#define __CMPXCHG_CASE(w, sz, name, mb, cl...) \
static inline unsigned long __cmpxchg_case_##name(volatile void *ptr, \
unsigned long old, \
unsigned long new) \
{ \
register unsigned long x0 asm ("x0") = (unsigned long)ptr; \
register unsigned long x1 asm ("x1") = old; \
register unsigned long x2 asm ("x2") = new; \
\
asm volatile(ARM64_LSE_ATOMIC_INSN( \
/* LL/SC */ \
" nop\n" \
__LL_SC_CMPXCHG(name) \
" nop", \
/* LSE atomics */ \
" mov " #w "30, %" #w "[old]\n" \
" cas" #mb #sz "\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) \
: "x30" , ##cl); \
\
return x0; \
}
__CMPXCHG_CASE(w, b, 1, )
__CMPXCHG_CASE(w, h, 2, )
__CMPXCHG_CASE(w, , 4, )
__CMPXCHG_CASE(x, , 8, )
__CMPXCHG_CASE(w, b, mb_1, al, "memory")
__CMPXCHG_CASE(w, h, mb_2, al, "memory")
__CMPXCHG_CASE(w, , mb_4, al, "memory")
__CMPXCHG_CASE(x, , mb_8, 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 int __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 */ \
" nop\n" \
" nop\n" \
" nop\n" \
__LL_SC_CMPXCHG_DBL(name), \
/* 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) \
: "x30" , ##cl); \
\
return x0; \
}
__CMPXCHG_DBL( , )
__CMPXCHG_DBL(_mb, al, "memory")
#undef __LL_SC_CMPXCHG_DBL
#undef __CMPXCHG_DBL
#endif /* __ASM_ATOMIC_LSE_H */
|