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
|
/* SPDX-License-Identifier: GPL-2.0-only */
/*
* Copyright (C) 2014 Regents of the University of California
*/
#ifndef _ASM_RISCV_CMPXCHG_H
#define _ASM_RISCV_CMPXCHG_H
#include <linux/bug.h>
#include <asm/fence.h>
#define __arch_xchg_masked(sc_sfx, prepend, append, r, p, n) \
({ \
u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \
ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \
ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \
<< __s; \
ulong __newx = (ulong)(n) << __s; \
ulong __retx; \
ulong __rc; \
\
__asm__ __volatile__ ( \
prepend \
"0: lr.w %0, %2\n" \
" and %1, %0, %z4\n" \
" or %1, %1, %z3\n" \
" sc.w" sc_sfx " %1, %1, %2\n" \
" bnez %1, 0b\n" \
append \
: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \
: "rJ" (__newx), "rJ" (~__mask) \
: "memory"); \
\
r = (__typeof__(*(p)))((__retx & __mask) >> __s); \
})
#define __arch_xchg(sfx, prepend, append, r, p, n) \
({ \
__asm__ __volatile__ ( \
prepend \
" amoswap" sfx " %0, %2, %1\n" \
append \
: "=r" (r), "+A" (*(p)) \
: "r" (n) \
: "memory"); \
})
#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \
sc_append, swap_append) \
({ \
__typeof__(ptr) __ptr = (ptr); \
__typeof__(*(__ptr)) __new = (new); \
__typeof__(*(__ptr)) __ret; \
\
switch (sizeof(*__ptr)) { \
case 1: \
case 2: \
__arch_xchg_masked(sc_sfx, prepend, sc_append, \
__ret, __ptr, __new); \
break; \
case 4: \
__arch_xchg(".w" swap_sfx, prepend, swap_append, \
__ret, __ptr, __new); \
break; \
case 8: \
__arch_xchg(".d" swap_sfx, prepend, swap_append, \
__ret, __ptr, __new); \
break; \
default: \
BUILD_BUG(); \
} \
(__typeof__(*(__ptr)))__ret; \
})
#define arch_xchg_relaxed(ptr, x) \
_arch_xchg(ptr, x, "", "", "", "", "")
#define arch_xchg_acquire(ptr, x) \
_arch_xchg(ptr, x, "", "", "", \
RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER)
#define arch_xchg_release(ptr, x) \
_arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "")
#define arch_xchg(ptr, x) \
_arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "")
#define xchg32(ptr, x) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 4); \
arch_xchg((ptr), (x)); \
})
#define xchg64(ptr, x) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_xchg((ptr), (x)); \
})
/*
* Atomic compare and exchange. Compare OLD with MEM, if identical,
* store NEW in MEM. Return the initial value in MEM. Success is
* indicated by comparing RETURN with OLD.
*/
#define __arch_cmpxchg_masked(sc_sfx, prepend, append, r, p, o, n) \
({ \
u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \
ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \
ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \
<< __s; \
ulong __newx = (ulong)(n) << __s; \
ulong __oldx = (ulong)(o) << __s; \
ulong __retx; \
ulong __rc; \
\
__asm__ __volatile__ ( \
prepend \
"0: lr.w %0, %2\n" \
" and %1, %0, %z5\n" \
" bne %1, %z3, 1f\n" \
" and %1, %0, %z6\n" \
" or %1, %1, %z4\n" \
" sc.w" sc_sfx " %1, %1, %2\n" \
" bnez %1, 0b\n" \
append \
"1:\n" \
: "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \
: "rJ" ((long)__oldx), "rJ" (__newx), \
"rJ" (__mask), "rJ" (~__mask) \
: "memory"); \
\
r = (__typeof__(*(p)))((__retx & __mask) >> __s); \
})
#define __arch_cmpxchg(lr_sfx, sc_sfx, prepend, append, r, p, co, o, n) \
({ \
register unsigned int __rc; \
\
__asm__ __volatile__ ( \
prepend \
"0: lr" lr_sfx " %0, %2\n" \
" bne %0, %z3, 1f\n" \
" sc" sc_sfx " %1, %z4, %2\n" \
" bnez %1, 0b\n" \
append \
"1:\n" \
: "=&r" (r), "=&r" (__rc), "+A" (*(p)) \
: "rJ" (co o), "rJ" (n) \
: "memory"); \
})
#define _arch_cmpxchg(ptr, old, new, sc_sfx, prepend, append) \
({ \
__typeof__(ptr) __ptr = (ptr); \
__typeof__(*(__ptr)) __old = (old); \
__typeof__(*(__ptr)) __new = (new); \
__typeof__(*(__ptr)) __ret; \
\
switch (sizeof(*__ptr)) { \
case 1: \
case 2: \
__arch_cmpxchg_masked(sc_sfx, prepend, append, \
__ret, __ptr, __old, __new); \
break; \
case 4: \
__arch_cmpxchg(".w", ".w" sc_sfx, prepend, append, \
__ret, __ptr, (long), __old, __new); \
break; \
case 8: \
__arch_cmpxchg(".d", ".d" sc_sfx, prepend, append, \
__ret, __ptr, /**/, __old, __new); \
break; \
default: \
BUILD_BUG(); \
} \
(__typeof__(*(__ptr)))__ret; \
})
#define arch_cmpxchg_relaxed(ptr, o, n) \
_arch_cmpxchg((ptr), (o), (n), "", "", "")
#define arch_cmpxchg_acquire(ptr, o, n) \
_arch_cmpxchg((ptr), (o), (n), "", "", RISCV_ACQUIRE_BARRIER)
#define arch_cmpxchg_release(ptr, o, n) \
_arch_cmpxchg((ptr), (o), (n), "", RISCV_RELEASE_BARRIER, "")
#define arch_cmpxchg(ptr, o, n) \
_arch_cmpxchg((ptr), (o), (n), ".rl", "", " fence rw, rw\n")
#define arch_cmpxchg_local(ptr, o, n) \
arch_cmpxchg_relaxed((ptr), (o), (n))
#define arch_cmpxchg64(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_cmpxchg((ptr), (o), (n)); \
})
#define arch_cmpxchg64_local(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_cmpxchg_relaxed((ptr), (o), (n)); \
})
#define arch_cmpxchg64_relaxed(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_cmpxchg_relaxed((ptr), (o), (n)); \
})
#define arch_cmpxchg64_acquire(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_cmpxchg_acquire((ptr), (o), (n)); \
})
#define arch_cmpxchg64_release(ptr, o, n) \
({ \
BUILD_BUG_ON(sizeof(*(ptr)) != 8); \
arch_cmpxchg_release((ptr), (o), (n)); \
})
#endif /* _ASM_RISCV_CMPXCHG_H */
|
