summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/include/asm/atomic.h
blob: 853dc86864f484c031d1351ad36504846c0c5aad (plain)
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_POWERPC_ATOMIC_H_
#define _ASM_POWERPC_ATOMIC_H_

/*
 * PowerPC atomic operations
 */

#ifdef __KERNEL__
#include <linux/types.h>
#include <asm/cmpxchg.h>
#include <asm/barrier.h>
#include <asm/asm-const.h>

/*
 * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
 * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
 * on the platform without lwsync.
 */
#define __atomic_acquire_fence()					\
	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")

#define __atomic_release_fence()					\
	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")

static __inline__ int arch_atomic_read(const atomic_t *v)
{
	int t;

	__asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));

	return t;
}

static __inline__ void arch_atomic_set(atomic_t *v, int i)
{
	__asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
}

#define ATOMIC_OP(op, asm_op, suffix, sign, ...)			\
static __inline__ void arch_atomic_##op(int a, atomic_t *v)		\
{									\
	int t;								\
									\
	__asm__ __volatile__(						\
"1:	lwarx	%0,0,%3		# atomic_" #op "\n"			\
	#asm_op "%I2" suffix " %0,%0,%2\n"				\
"	stwcx.	%0,0,%3 \n"						\
"	bne-	1b\n"							\
	: "=&r" (t), "+m" (v->counter)					\
	: "r"#sign (a), "r" (&v->counter)				\
	: "cc", ##__VA_ARGS__);						\
}									\

#define ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ...)		\
static inline int arch_atomic_##op##_return_relaxed(int a, atomic_t *v)	\
{									\
	int t;								\
									\
	__asm__ __volatile__(						\
"1:	lwarx	%0,0,%3		# atomic_" #op "_return_relaxed\n"	\
	#asm_op "%I2" suffix " %0,%0,%2\n"				\
"	stwcx.	%0,0,%3\n"						\
"	bne-	1b\n"							\
	: "=&r" (t), "+m" (v->counter)					\
	: "r"#sign (a), "r" (&v->counter)				\
	: "cc", ##__VA_ARGS__);						\
									\
	return t;							\
}

#define ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ...)		\
static inline int arch_atomic_fetch_##op##_relaxed(int a, atomic_t *v)	\
{									\
	int res, t;							\
									\
	__asm__ __volatile__(						\
"1:	lwarx	%0,0,%4		# atomic_fetch_" #op "_relaxed\n"	\
	#asm_op "%I3" suffix " %1,%0,%3\n"				\
"	stwcx.	%1,0,%4\n"						\
"	bne-	1b\n"							\
	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
	: "r"#sign (a), "r" (&v->counter)				\
	: "cc", ##__VA_ARGS__);						\
									\
	return res;							\
}

#define ATOMIC_OPS(op, asm_op, suffix, sign, ...)			\
	ATOMIC_OP(op, asm_op, suffix, sign, ##__VA_ARGS__)		\
	ATOMIC_OP_RETURN_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)\
	ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign, ##__VA_ARGS__)

ATOMIC_OPS(add, add, "c", I, "xer")
ATOMIC_OPS(sub, sub, "c", I, "xer")

#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_fetch_add_relaxed arch_atomic_fetch_add_relaxed
#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed

#undef ATOMIC_OPS
#define ATOMIC_OPS(op, asm_op, suffix, sign)				\
	ATOMIC_OP(op, asm_op, suffix, sign)				\
	ATOMIC_FETCH_OP_RELAXED(op, asm_op, suffix, sign)

ATOMIC_OPS(and, and, ".", K)
ATOMIC_OPS(or, or, "", K)
ATOMIC_OPS(xor, xor, "", K)

#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

#undef ATOMIC_OPS
#undef ATOMIC_FETCH_OP_RELAXED
#undef ATOMIC_OP_RETURN_RELAXED
#undef ATOMIC_OP

#define arch_atomic_cmpxchg(v, o, n) \
	(arch_cmpxchg(&((v)->counter), (o), (n)))
#define arch_atomic_cmpxchg_relaxed(v, o, n) \
	arch_cmpxchg_relaxed(&((v)->counter), (o), (n))
#define arch_atomic_cmpxchg_acquire(v, o, n) \
	arch_cmpxchg_acquire(&((v)->counter), (o), (n))

#define arch_atomic_xchg(v, new) \
	(arch_xchg(&((v)->counter), new))
#define arch_atomic_xchg_relaxed(v, new) \
	arch_xchg_relaxed(&((v)->counter), (new))

/*
 * Don't want to override the generic atomic_try_cmpxchg_acquire, because
 * we add a lock hint to the lwarx, which may not be wanted for the
 * _acquire case (and is not used by the other _acquire variants so it
 * would be a surprise).
 */
static __always_inline bool
arch_atomic_try_cmpxchg_lock(atomic_t *v, int *old, int new)
{
	int r, o = *old;

	__asm__ __volatile__ (
"1:	lwarx	%0,0,%2,%5	# atomic_try_cmpxchg_acquire		\n"
"	cmpw	0,%0,%3							\n"
"	bne-	2f							\n"
"	stwcx.	%4,0,%2							\n"
"	bne-	1b							\n"
"\t"	PPC_ACQUIRE_BARRIER "						\n"
"2:									\n"
	: "=&r" (r), "+m" (v->counter)
	: "r" (&v->counter), "r" (o), "r" (new), "i" (IS_ENABLED(CONFIG_PPC64) ? 1 : 0)
	: "cr0", "memory");

	if (unlikely(r != o))
		*old = r;
	return likely(r == o);
}

/**
 * atomic_fetch_add_unless - add unless the number is a given value
 * @v: pointer of type atomic_t
 * @a: the amount to add to v...
 * @u: ...unless v is equal to u.
 *
 * Atomically adds @a to @v, so long as it was not @u.
 * Returns the old value of @v.
 */
static __inline__ int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
	int t;

	__asm__ __volatile__ (
	PPC_ATOMIC_ENTRY_BARRIER
"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
	cmpw	0,%0,%3 \n\
	beq	2f \n\
	add%I2c	%0,%0,%2 \n"
"	stwcx.	%0,0,%1 \n\
	bne-	1b \n"
	PPC_ATOMIC_EXIT_BARRIER
"	sub%I2c	%0,%0,%2 \n\
2:"
	: "=&r" (t)
	: "r" (&v->counter), "rI" (a), "r" (u)
	: "cc", "memory", "xer");

	return t;
}
#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless

/*
 * Atomically test *v and decrement if it is greater than 0.
 * The function returns the old value of *v minus 1, even if
 * the atomic variable, v, was not decremented.
 */
static __inline__ int arch_atomic_dec_if_positive(atomic_t *v)
{
	int t;

	__asm__ __volatile__(
	PPC_ATOMIC_ENTRY_BARRIER
"1:	lwarx	%0,0,%1		# atomic_dec_if_positive\n\
	cmpwi	%0,1\n\
	addi	%0,%0,-1\n\
	blt-	2f\n"
"	stwcx.	%0,0,%1\n\
	bne-	1b"
	PPC_ATOMIC_EXIT_BARRIER
	"\n\
2:"	: "=&b" (t)
	: "r" (&v->counter)
	: "cc", "memory");

	return t;
}
#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive

#ifdef __powerpc64__

#define ATOMIC64_INIT(i)	{ (i) }

static __inline__ s64 arch_atomic64_read(const atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));

	return t;
}

static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i)
{
	__asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
}

#define ATOMIC64_OP(op, asm_op)						\
static __inline__ void arch_atomic64_##op(s64 a, atomic64_t *v)		\
{									\
	s64 t;								\
									\
	__asm__ __volatile__(						\
"1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
	#asm_op " %0,%2,%0\n"						\
"	stdcx.	%0,0,%3 \n"						\
"	bne-	1b\n"							\
	: "=&r" (t), "+m" (v->counter)					\
	: "r" (a), "r" (&v->counter)					\
	: "cc");							\
}

#define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
static inline s64							\
arch_atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)		\
{									\
	s64 t;								\
									\
	__asm__ __volatile__(						\
"1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
	#asm_op " %0,%2,%0\n"						\
"	stdcx.	%0,0,%3\n"						\
"	bne-	1b\n"							\
	: "=&r" (t), "+m" (v->counter)					\
	: "r" (a), "r" (&v->counter)					\
	: "cc");							\
									\
	return t;							\
}

#define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
static inline s64							\
arch_atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)		\
{									\
	s64 res, t;							\
									\
	__asm__ __volatile__(						\
"1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
	#asm_op " %1,%3,%0\n"						\
"	stdcx.	%1,0,%4\n"						\
"	bne-	1b\n"							\
	: "=&r" (res), "=&r" (t), "+m" (v->counter)			\
	: "r" (a), "r" (&v->counter)					\
	: "cc");							\
									\
	return res;							\
}

#define ATOMIC64_OPS(op, asm_op)					\
	ATOMIC64_OP(op, asm_op)						\
	ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)

ATOMIC64_OPS(add, add)
ATOMIC64_OPS(sub, subf)

#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_fetch_add_relaxed arch_atomic64_fetch_add_relaxed
#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed

#undef ATOMIC64_OPS
#define ATOMIC64_OPS(op, asm_op)					\
	ATOMIC64_OP(op, asm_op)						\
	ATOMIC64_FETCH_OP_RELAXED(op, asm_op)

ATOMIC64_OPS(and, and)
ATOMIC64_OPS(or, or)
ATOMIC64_OPS(xor, xor)

#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

#undef ATOPIC64_OPS
#undef ATOMIC64_FETCH_OP_RELAXED
#undef ATOMIC64_OP_RETURN_RELAXED
#undef ATOMIC64_OP

static __inline__ void arch_atomic64_inc(atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__(
"1:	ldarx	%0,0,%2		# atomic64_inc\n\
	addic	%0,%0,1\n\
	stdcx.	%0,0,%2 \n\
	bne-	1b"
	: "=&r" (t), "+m" (v->counter)
	: "r" (&v->counter)
	: "cc", "xer");
}
#define arch_atomic64_inc arch_atomic64_inc

static __inline__ s64 arch_atomic64_inc_return_relaxed(atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__(
"1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
"	addic	%0,%0,1\n"
"	stdcx.	%0,0,%2\n"
"	bne-	1b"
	: "=&r" (t), "+m" (v->counter)
	: "r" (&v->counter)
	: "cc", "xer");

	return t;
}

static __inline__ void arch_atomic64_dec(atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__(
"1:	ldarx	%0,0,%2		# atomic64_dec\n\
	addic	%0,%0,-1\n\
	stdcx.	%0,0,%2\n\
	bne-	1b"
	: "=&r" (t), "+m" (v->counter)
	: "r" (&v->counter)
	: "cc", "xer");
}
#define arch_atomic64_dec arch_atomic64_dec

static __inline__ s64 arch_atomic64_dec_return_relaxed(atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__(
"1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
"	addic	%0,%0,-1\n"
"	stdcx.	%0,0,%2\n"
"	bne-	1b"
	: "=&r" (t), "+m" (v->counter)
	: "r" (&v->counter)
	: "cc", "xer");

	return t;
}

#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed
#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed

/*
 * Atomically test *v and decrement if it is greater than 0.
 * The function returns the old value of *v minus 1.
 */
static __inline__ s64 arch_atomic64_dec_if_positive(atomic64_t *v)
{
	s64 t;

	__asm__ __volatile__(
	PPC_ATOMIC_ENTRY_BARRIER
"1:	ldarx	%0,0,%1		# atomic64_dec_if_positive\n\
	addic.	%0,%0,-1\n\
	blt-	2f\n\
	stdcx.	%0,0,%1\n\
	bne-	1b"
	PPC_ATOMIC_EXIT_BARRIER
	"\n\
2:"	: "=&r" (t)
	: "r" (&v->counter)
	: "cc", "xer", "memory");

	return t;
}
#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive

#define arch_atomic64_cmpxchg(v, o, n) \
	(arch_cmpxchg(&((v)->counter), (o), (n)))
#define arch_atomic64_cmpxchg_relaxed(v, o, n) \
	arch_cmpxchg_relaxed(&((v)->counter), (o), (n))
#define arch_atomic64_cmpxchg_acquire(v, o, n) \
	arch_cmpxchg_acquire(&((v)->counter), (o), (n))

#define arch_atomic64_xchg(v, new) \
	(arch_xchg(&((v)->counter), new))
#define arch_atomic64_xchg_relaxed(v, new) \
	arch_xchg_relaxed(&((v)->counter), (new))

/**
 * atomic64_fetch_add_unless - add unless the number is a given value
 * @v: pointer of type atomic64_t
 * @a: the amount to add to v...
 * @u: ...unless v is equal to u.
 *
 * Atomically adds @a to @v, so long as it was not @u.
 * Returns the old value of @v.
 */
static __inline__ s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
	s64 t;

	__asm__ __volatile__ (
	PPC_ATOMIC_ENTRY_BARRIER
"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
	cmpd	0,%0,%3 \n\
	beq	2f \n\
	add	%0,%2,%0 \n"
"	stdcx.	%0,0,%1 \n\
	bne-	1b \n"
	PPC_ATOMIC_EXIT_BARRIER
"	subf	%0,%2,%0 \n\
2:"
	: "=&r" (t)
	: "r" (&v->counter), "r" (a), "r" (u)
	: "cc", "memory");

	return t;
}
#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless

/**
 * atomic_inc64_not_zero - increment unless the number is zero
 * @v: pointer of type atomic64_t
 *
 * Atomically increments @v by 1, so long as @v is non-zero.
 * Returns non-zero if @v was non-zero, and zero otherwise.
 */
static __inline__ int arch_atomic64_inc_not_zero(atomic64_t *v)
{
	s64 t1, t2;

	__asm__ __volatile__ (
	PPC_ATOMIC_ENTRY_BARRIER
"1:	ldarx	%0,0,%2		# atomic64_inc_not_zero\n\
	cmpdi	0,%0,0\n\
	beq-	2f\n\
	addic	%1,%0,1\n\
	stdcx.	%1,0,%2\n\
	bne-	1b\n"
	PPC_ATOMIC_EXIT_BARRIER
	"\n\
2:"
	: "=&r" (t1), "=&r" (t2)
	: "r" (&v->counter)
	: "cc", "xer", "memory");

	return t1 != 0;
}
#define arch_atomic64_inc_not_zero(v) arch_atomic64_inc_not_zero((v))

#endif /* __powerpc64__ */

#endif /* __KERNEL__ */
#endif /* _ASM_POWERPC_ATOMIC_H_ */