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
|
#ifndef _ASM_X86_CMPXCHG_32_H
#define _ASM_X86_CMPXCHG_32_H
#include <linux/bitops.h> /* for LOCK_PREFIX */
/*
* Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
* you need to test for the feature in boot_cpu_data.
*/
extern void __xchg_wrong_size(void);
/*
* Note: no "lock" prefix even on SMP: xchg always implies lock anyway.
* Since this is generally used to protect other memory information, we
* use "asm volatile" and "memory" clobbers to prevent gcc from moving
* information around.
*/
#define __xchg(x, ptr, size) \
({ \
__typeof(*(ptr)) __x = (x); \
switch (size) { \
case 1: \
{ \
volatile u8 *__ptr = (volatile u8 *)(ptr); \
asm volatile("xchgb %0,%1" \
: "=q" (__x), "+m" (*__ptr) \
: "0" (__x) \
: "memory"); \
break; \
} \
case 2: \
{ \
volatile u16 *__ptr = (volatile u16 *)(ptr); \
asm volatile("xchgw %0,%1" \
: "=r" (__x), "+m" (*__ptr) \
: "0" (__x) \
: "memory"); \
break; \
} \
case 4: \
{ \
volatile u32 *__ptr = (volatile u32 *)(ptr); \
asm volatile("xchgl %0,%1" \
: "=r" (__x), "+m" (*__ptr) \
: "0" (__x) \
: "memory"); \
break; \
} \
default: \
__xchg_wrong_size(); \
} \
__x; \
})
#define xchg(ptr, v) \
__xchg((v), (ptr), sizeof(*ptr))
/*
* CMPXCHG8B only writes to the target if we had the previous
* value in registers, otherwise it acts as a read and gives us the
* "new previous" value. That is why there is a loop. Preloading
* EDX:EAX is a performance optimization: in the common case it means
* we need only one locked operation.
*
* A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very
* least an FPU save and/or %cr0.ts manipulation.
*
* cmpxchg8b must be used with the lock prefix here to allow the
* instruction to be executed atomically. We need to have the reader
* side to see the coherent 64bit value.
*/
static inline void set_64bit(volatile u64 *ptr, u64 value)
{
u32 low = value;
u32 high = value >> 32;
u64 prev = *ptr;
asm volatile("\n1:\t"
LOCK_PREFIX "cmpxchg8b %0\n\t"
"jnz 1b"
: "=m" (*ptr), "+A" (prev)
: "b" (low), "c" (high)
: "memory");
}
extern void __cmpxchg_wrong_size(void);
/*
* 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 __raw_cmpxchg(ptr, old, new, size, lock) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (old); \
__typeof__(*(ptr)) __new = (new); \
switch (size) { \
case 1: \
{ \
volatile u8 *__ptr = (volatile u8 *)(ptr); \
asm volatile(lock "cmpxchgb %2,%1" \
: "=a" (__ret), "+m" (*__ptr) \
: "q" (__new), "0" (__old) \
: "memory"); \
break; \
} \
case 2: \
{ \
volatile u16 *__ptr = (volatile u16 *)(ptr); \
asm volatile(lock "cmpxchgw %2,%1" \
: "=a" (__ret), "+m" (*__ptr) \
: "r" (__new), "0" (__old) \
: "memory"); \
break; \
} \
case 4: \
{ \
volatile u32 *__ptr = (volatile u32 *)(ptr); \
asm volatile(lock "cmpxchgl %2,%1" \
: "=a" (__ret), "+m" (*__ptr) \
: "r" (__new), "0" (__old) \
: "memory"); \
break; \
} \
default: \
__cmpxchg_wrong_size(); \
} \
__ret; \
})
#define __cmpxchg(ptr, old, new, size) \
__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)
#define __sync_cmpxchg(ptr, old, new, size) \
__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")
#define __cmpxchg_local(ptr, old, new, size) \
__raw_cmpxchg((ptr), (old), (new), (size), "")
#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr, old, new) \
__cmpxchg((ptr), (old), (new), sizeof(*ptr))
#define sync_cmpxchg(ptr, old, new) \
__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))
#define cmpxchg_local(ptr, old, new) \
__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
#endif
#ifdef CONFIG_X86_CMPXCHG64
#define cmpxchg64(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
(unsigned long long)(n)))
#define cmpxchg64_local(ptr, o, n) \
((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
(unsigned long long)(n)))
#endif
static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
{
u64 prev;
asm volatile(LOCK_PREFIX "cmpxchg8b %1"
: "=A" (prev),
"+m" (*ptr)
: "b" ((u32)new),
"c" ((u32)(new >> 32)),
"0" (old)
: "memory");
return prev;
}
static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
{
u64 prev;
asm volatile("cmpxchg8b %1"
: "=A" (prev),
"+m" (*ptr)
: "b" ((u32)new),
"c" ((u32)(new >> 32)),
"0" (old)
: "memory");
return prev;
}
#ifndef CONFIG_X86_CMPXCHG
/*
* Building a kernel capable running on 80386. It may be necessary to
* simulate the cmpxchg on the 80386 CPU. For that purpose we define
* a function for each of the sizes we support.
*/
extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
switch (size) {
case 1:
return cmpxchg_386_u8(ptr, old, new);
case 2:
return cmpxchg_386_u16(ptr, old, new);
case 4:
return cmpxchg_386_u32(ptr, old, new);
}
return old;
}
#define cmpxchg(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
if (likely(boot_cpu_data.x86 > 3)) \
__ret = (__typeof__(*(ptr)))__cmpxchg((ptr), \
(unsigned long)(o), (unsigned long)(n), \
sizeof(*(ptr))); \
else \
__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
(unsigned long)(o), (unsigned long)(n), \
sizeof(*(ptr))); \
__ret; \
})
#define cmpxchg_local(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
if (likely(boot_cpu_data.x86 > 3)) \
__ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr), \
(unsigned long)(o), (unsigned long)(n), \
sizeof(*(ptr))); \
else \
__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr), \
(unsigned long)(o), (unsigned long)(n), \
sizeof(*(ptr))); \
__ret; \
})
#endif
#ifndef CONFIG_X86_CMPXCHG64
/*
* Building a kernel capable running on 80386 and 80486. It may be necessary
* to simulate the cmpxchg8b on the 80386 and 80486 CPU.
*/
#define cmpxchg64(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (o); \
__typeof__(*(ptr)) __new = (n); \
alternative_io(LOCK_PREFIX_HERE \
"call cmpxchg8b_emu", \
"lock; cmpxchg8b (%%esi)" , \
X86_FEATURE_CX8, \
"=A" (__ret), \
"S" ((ptr)), "0" (__old), \
"b" ((unsigned int)__new), \
"c" ((unsigned int)(__new>>32)) \
: "memory"); \
__ret; })
#define cmpxchg64_local(ptr, o, n) \
({ \
__typeof__(*(ptr)) __ret; \
__typeof__(*(ptr)) __old = (o); \
__typeof__(*(ptr)) __new = (n); \
alternative_io("call cmpxchg8b_emu", \
"cmpxchg8b (%%esi)" , \
X86_FEATURE_CX8, \
"=A" (__ret), \
"S" ((ptr)), "0" (__old), \
"b" ((unsigned int)__new), \
"c" ((unsigned int)(__new>>32)) \
: "memory"); \
__ret; })
#endif
#endif /* _ASM_X86_CMPXCHG_32_H */
|
