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
|
#ifndef __ASM_ARM_CMPXCHG_H
#define __ASM_ARM_CMPXCHG_H
#include <linux/irqflags.h>
#include <linux/prefetch.h>
#include <asm/barrier.h>
#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
/*
* On the StrongARM, "swp" is terminally broken since it bypasses the
* cache totally. This means that the cache becomes inconsistent, and,
* since we use normal loads/stores as well, this is really bad.
* Typically, this causes oopsen in filp_close, but could have other,
* more disastrous effects. There are two work-arounds:
* 1. Disable interrupts and emulate the atomic swap
* 2. Clean the cache, perform atomic swap, flush the cache
*
* We choose (1) since its the "easiest" to achieve here and is not
* dependent on the processor type.
*
* NOTE that this solution won't work on an SMP system, so explcitly
* forbid it here.
*/
#define swp_is_buggy
#endif
static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
{
extern void __bad_xchg(volatile void *, int);
unsigned long ret;
#ifdef swp_is_buggy
unsigned long flags;
#endif
#if __LINUX_ARM_ARCH__ >= 6
unsigned int tmp;
#endif
smp_mb();
prefetchw((const void *)ptr);
switch (size) {
#if __LINUX_ARM_ARCH__ >= 6
case 1:
asm volatile("@ __xchg1\n"
"1: ldrexb %0, [%3]\n"
" strexb %1, %2, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (ret), "=&r" (tmp)
: "r" (x), "r" (ptr)
: "memory", "cc");
break;
case 4:
asm volatile("@ __xchg4\n"
"1: ldrex %0, [%3]\n"
" strex %1, %2, [%3]\n"
" teq %1, #0\n"
" bne 1b"
: "=&r" (ret), "=&r" (tmp)
: "r" (x), "r" (ptr)
: "memory", "cc");
break;
#elif defined(swp_is_buggy)
#ifdef CONFIG_SMP
#error SMP is not supported on this platform
#endif
case 1:
raw_local_irq_save(flags);
ret = *(volatile unsigned char *)ptr;
*(volatile unsigned char *)ptr = x;
raw_local_irq_restore(flags);
break;
case 4:
raw_local_irq_save(flags);
ret = *(volatile unsigned long *)ptr;
*(volatile unsigned long *)ptr = x;
raw_local_irq_restore(flags);
break;
#else
case 1:
asm volatile("@ __xchg1\n"
" swpb %0, %1, [%2]"
: "=&r" (ret)
: "r" (x), "r" (ptr)
: "memory", "cc");
break;
case 4:
asm volatile("@ __xchg4\n"
" swp %0, %1, [%2]"
: "=&r" (ret)
: "r" (x), "r" (ptr)
: "memory", "cc");
break;
#endif
default:
/* Cause a link-time error, the xchg() size is not supported */
__bad_xchg(ptr, size), ret = 0;
break;
}
smp_mb();
return ret;
}
#define xchg(ptr, x) ({ \
(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), \
sizeof(*(ptr))); \
})
#include <asm-generic/cmpxchg-local.h>
#if __LINUX_ARM_ARCH__ < 6
/* min ARCH < ARMv6 */
#ifdef CONFIG_SMP
#error "SMP is not supported on this platform"
#endif
/*
* cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
* them available.
*/
#define cmpxchg_local(ptr, o, n) ({ \
(__typeof(*ptr))__cmpxchg_local_generic((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))); \
})
#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
#include <asm-generic/cmpxchg.h>
#else /* min ARCH >= ARMv6 */
extern void __bad_cmpxchg(volatile void *ptr, int size);
/*
* cmpxchg only support 32-bits operands on ARMv6.
*/
static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
unsigned long oldval, res;
prefetchw((const void *)ptr);
switch (size) {
#ifndef CONFIG_CPU_V6 /* min ARCH >= ARMv6K */
case 1:
do {
asm volatile("@ __cmpxchg1\n"
" ldrexb %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexbeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
case 2:
do {
asm volatile("@ __cmpxchg1\n"
" ldrexh %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexheq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
#endif
case 4:
do {
asm volatile("@ __cmpxchg4\n"
" ldrex %1, [%2]\n"
" mov %0, #0\n"
" teq %1, %3\n"
" strexeq %0, %4, [%2]\n"
: "=&r" (res), "=&r" (oldval)
: "r" (ptr), "Ir" (old), "r" (new)
: "memory", "cc");
} while (res);
break;
default:
__bad_cmpxchg(ptr, size);
oldval = 0;
}
return oldval;
}
static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
unsigned long new, int size)
{
unsigned long ret;
smp_mb();
ret = __cmpxchg(ptr, old, new, size);
smp_mb();
return ret;
}
#define cmpxchg(ptr,o,n) ({ \
(__typeof__(*(ptr)))__cmpxchg_mb((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))); \
})
static inline unsigned long __cmpxchg_local(volatile void *ptr,
unsigned long old,
unsigned long new, int size)
{
unsigned long ret;
switch (size) {
#ifdef CONFIG_CPU_V6 /* min ARCH == ARMv6 */
case 1:
case 2:
ret = __cmpxchg_local_generic(ptr, old, new, size);
break;
#endif
default:
ret = __cmpxchg(ptr, old, new, size);
}
return ret;
}
#define cmpxchg_local(ptr, o, n) ({ \
(__typeof(*ptr))__cmpxchg_local((ptr), \
(unsigned long)(o), \
(unsigned long)(n), \
sizeof(*(ptr))); \
})
static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
unsigned long long old,
unsigned long long new)
{
unsigned long long oldval;
unsigned long res;
prefetchw(ptr);
__asm__ __volatile__(
"1: ldrexd %1, %H1, [%3]\n"
" teq %1, %4\n"
" teqeq %H1, %H4\n"
" bne 2f\n"
" strexd %0, %5, %H5, [%3]\n"
" teq %0, #0\n"
" bne 1b\n"
"2:"
: "=&r" (res), "=&r" (oldval), "+Qo" (*ptr)
: "r" (ptr), "r" (old), "r" (new)
: "cc");
return oldval;
}
#define cmpxchg64_relaxed(ptr, o, n) ({ \
(__typeof__(*(ptr)))__cmpxchg64((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)); \
})
#define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
unsigned long long old,
unsigned long long new)
{
unsigned long long ret;
smp_mb();
ret = __cmpxchg64(ptr, old, new);
smp_mb();
return ret;
}
#define cmpxchg64(ptr, o, n) ({ \
(__typeof__(*(ptr)))__cmpxchg64_mb((ptr), \
(unsigned long long)(o), \
(unsigned long long)(n)); \
})
#endif /* __LINUX_ARM_ARCH__ >= 6 */
#endif /* __ASM_ARM_CMPXCHG_H */
|
