summaryrefslogtreecommitdiffstats
path: root/include/asm-generic/barrier.h
blob: 3d503e74037fd9d1f191854dea0758b17bc05520 (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * Generic barrier definitions.
 *
 * It should be possible to use these on really simple architectures,
 * but it serves more as a starting point for new ports.
 *
 * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
 * Written by David Howells (dhowells@redhat.com)
 */
#ifndef __ASM_GENERIC_BARRIER_H
#define __ASM_GENERIC_BARRIER_H

#ifndef __ASSEMBLY__

#include <linux/compiler.h>
#include <linux/kcsan-checks.h>
#include <asm/rwonce.h>

#ifndef nop
#define nop()	asm volatile ("nop")
#endif

/*
 * Architectures that want generic instrumentation can define __ prefixed
 * variants of all barriers.
 */

#ifdef __mb
#define mb()	do { kcsan_mb(); __mb(); } while (0)
#endif

#ifdef __rmb
#define rmb()	do { kcsan_rmb(); __rmb(); } while (0)
#endif

#ifdef __wmb
#define wmb()	do { kcsan_wmb(); __wmb(); } while (0)
#endif

#ifdef __dma_rmb
#define dma_rmb()	do { kcsan_rmb(); __dma_rmb(); } while (0)
#endif

#ifdef __dma_wmb
#define dma_wmb()	do { kcsan_wmb(); __dma_wmb(); } while (0)
#endif

/*
 * Force strict CPU ordering. And yes, this is required on UP too when we're
 * talking to devices.
 *
 * Fall back to compiler barriers if nothing better is provided.
 */

#ifndef mb
#define mb()	barrier()
#endif

#ifndef rmb
#define rmb()	mb()
#endif

#ifndef wmb
#define wmb()	mb()
#endif

#ifndef dma_rmb
#define dma_rmb()	rmb()
#endif

#ifndef dma_wmb
#define dma_wmb()	wmb()
#endif

#ifndef __smp_mb
#define __smp_mb()	mb()
#endif

#ifndef __smp_rmb
#define __smp_rmb()	rmb()
#endif

#ifndef __smp_wmb
#define __smp_wmb()	wmb()
#endif

#ifdef CONFIG_SMP

#ifndef smp_mb
#define smp_mb()	do { kcsan_mb(); __smp_mb(); } while (0)
#endif

#ifndef smp_rmb
#define smp_rmb()	do { kcsan_rmb(); __smp_rmb(); } while (0)
#endif

#ifndef smp_wmb
#define smp_wmb()	do { kcsan_wmb(); __smp_wmb(); } while (0)
#endif

#else	/* !CONFIG_SMP */

#ifndef smp_mb
#define smp_mb()	barrier()
#endif

#ifndef smp_rmb
#define smp_rmb()	barrier()
#endif

#ifndef smp_wmb
#define smp_wmb()	barrier()
#endif

#endif	/* CONFIG_SMP */

#ifndef __smp_store_mb
#define __smp_store_mb(var, value)  do { WRITE_ONCE(var, value); __smp_mb(); } while (0)
#endif

#ifndef __smp_mb__before_atomic
#define __smp_mb__before_atomic()	__smp_mb()
#endif

#ifndef __smp_mb__after_atomic
#define __smp_mb__after_atomic()	__smp_mb()
#endif

#ifndef __smp_store_release
#define __smp_store_release(p, v)					\
do {									\
	compiletime_assert_atomic_type(*p);				\
	__smp_mb();							\
	WRITE_ONCE(*p, v);						\
} while (0)
#endif

#ifndef __smp_load_acquire
#define __smp_load_acquire(p)						\
({									\
	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
	compiletime_assert_atomic_type(*p);				\
	__smp_mb();							\
	(typeof(*p))___p1;						\
})
#endif

#ifdef CONFIG_SMP

#ifndef smp_store_mb
#define smp_store_mb(var, value)  do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
#endif

#ifndef smp_mb__before_atomic
#define smp_mb__before_atomic()	do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
#endif

#ifndef smp_mb__after_atomic
#define smp_mb__after_atomic()	do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
#endif

#ifndef smp_store_release
#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
#endif

#ifndef smp_load_acquire
#define smp_load_acquire(p) __smp_load_acquire(p)
#endif

#else	/* !CONFIG_SMP */

#ifndef smp_store_mb
#define smp_store_mb(var, value)  do { WRITE_ONCE(var, value); barrier(); } while (0)
#endif

#ifndef smp_mb__before_atomic
#define smp_mb__before_atomic()	barrier()
#endif

#ifndef smp_mb__after_atomic
#define smp_mb__after_atomic()	barrier()
#endif

#ifndef smp_store_release
#define smp_store_release(p, v)						\
do {									\
	compiletime_assert_atomic_type(*p);				\
	barrier();							\
	WRITE_ONCE(*p, v);						\
} while (0)
#endif

#ifndef smp_load_acquire
#define smp_load_acquire(p)						\
({									\
	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
	compiletime_assert_atomic_type(*p);				\
	barrier();							\
	(typeof(*p))___p1;						\
})
#endif

#endif	/* CONFIG_SMP */

/* Barriers for virtual machine guests when talking to an SMP host */
#define virt_mb() do { kcsan_mb(); __smp_mb(); } while (0)
#define virt_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0)
#define virt_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0)
#define virt_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
#define virt_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
#define virt_mb__after_atomic()	do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
#define virt_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
#define virt_load_acquire(p) __smp_load_acquire(p)

/**
 * smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
 *
 * A control dependency provides a LOAD->STORE order, the additional RMB
 * provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
 * aka. (load)-ACQUIRE.
 *
 * Architectures that do not do load speculation can have this be barrier().
 */
#ifndef smp_acquire__after_ctrl_dep
#define smp_acquire__after_ctrl_dep()		smp_rmb()
#endif

/**
 * smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
 * @ptr: pointer to the variable to wait on
 * @cond: boolean expression to wait for
 *
 * Equivalent to using READ_ONCE() on the condition variable.
 *
 * Due to C lacking lambda expressions we load the value of *ptr into a
 * pre-named variable @VAL to be used in @cond.
 */
#ifndef smp_cond_load_relaxed
#define smp_cond_load_relaxed(ptr, cond_expr) ({		\
	typeof(ptr) __PTR = (ptr);				\
	__unqual_scalar_typeof(*ptr) VAL;			\
	for (;;) {						\
		VAL = READ_ONCE(*__PTR);			\
		if (cond_expr)					\
			break;					\
		cpu_relax();					\
	}							\
	(typeof(*ptr))VAL;					\
})
#endif

/**
 * smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
 * @ptr: pointer to the variable to wait on
 * @cond: boolean expression to wait for
 *
 * Equivalent to using smp_load_acquire() on the condition variable but employs
 * the control dependency of the wait to reduce the barrier on many platforms.
 */
#ifndef smp_cond_load_acquire
#define smp_cond_load_acquire(ptr, cond_expr) ({		\
	__unqual_scalar_typeof(*ptr) _val;			\
	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
	smp_acquire__after_ctrl_dep();				\
	(typeof(*ptr))_val;					\
})
#endif

/*
 * pmem_wmb() ensures that all stores for which the modification
 * are written to persistent storage by preceding instructions have
 * updated persistent storage before any data  access or data transfer
 * caused by subsequent instructions is initiated.
 */
#ifndef pmem_wmb
#define pmem_wmb()	wmb()
#endif

/*
 * ioremap_wc() maps I/O memory as memory with write-combining attributes. For
 * this kind of memory accesses, the CPU may wait for prior accesses to be
 * merged with subsequent ones. In some situation, such wait is bad for the
 * performance. io_stop_wc() can be used to prevent the merging of
 * write-combining memory accesses before this macro with those after it.
 */
#ifndef io_stop_wc
#define io_stop_wc do { } while (0)
#endif

#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */