summaryrefslogtreecommitdiffstats
path: root/include/asm-x86/cmpxchg_32.h
blob: f86ede28f6dc84750ab60250cc7d122534d9c74a (plain) (blame)
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
#ifndef __ASM_CMPXCHG_H
#define __ASM_CMPXCHG_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.
 */

#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))

struct __xchg_dummy { unsigned long a[100]; };
#define __xg(x) ((struct __xchg_dummy *)(x))

/*
 * The semantics of XCHGCMP8B are a bit strange, this is why
 * there is a loop and the loading of %%eax and %%edx has to
 * be inside. This inlines well in most cases, the cached
 * cost is around ~38 cycles. (in the future we might want
 * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
 * might have an implicit FPU-save as a cost, so it's not
 * clear which path to go.)
 *
 * cmpxchg8b must be used with the lock prefix here to allow
 * the instruction to be executed atomically, see page 3-102
 * of the instruction set reference 24319102.pdf. We need
 * the reader side to see the coherent 64bit value.
 */
static inline void __set_64bit (unsigned long long * ptr,
		unsigned int low, unsigned int high)
{
	__asm__ __volatile__ (
		"\n1:\t"
		"movl (%0), %%eax\n\t"
		"movl 4(%0), %%edx\n\t"
		LOCK_PREFIX "cmpxchg8b (%0)\n\t"
		"jnz 1b"
		: /* no outputs */
		:	"D"(ptr),
			"b"(low),
			"c"(high)
		:	"ax","dx","memory");
}

static inline void __set_64bit_constant (unsigned long long *ptr,
						 unsigned long long value)
{
	__set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
}
#define ll_low(x)	*(((unsigned int*)&(x))+0)
#define ll_high(x)	*(((unsigned int*)&(x))+1)

static inline void __set_64bit_var (unsigned long long *ptr,
			 unsigned long long value)
{
	__set_64bit(ptr,ll_low(value), ll_high(value));
}

#define set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit_constant(ptr, value) : \
 __set_64bit_var(ptr, value) )

#define _set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
 __set_64bit(ptr, ll_low(value), ll_high(value)) )

/*
 * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
 * Note 2: xchg has side effect, so that attribute volatile is necessary,
 *	  but generally the primitive is invalid, *ptr is output argument. --ANK
 */
static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
{
	switch (size) {
		case 1:
			__asm__ __volatile__("xchgb %b0,%1"
				:"=q" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 2:
			__asm__ __volatile__("xchgw %w0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 4:
			__asm__ __volatile__("xchgl %0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
	}
	return 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.
 */

#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#define sync_cmpxchg(ptr,o,n)\
	((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#define cmpxchg_local(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#endif

static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
				      unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

/*
 * Always use locked operations when touching memory shared with a
 * hypervisor, since the system may be SMP even if the guest kernel
 * isn't.
 */
static inline unsigned long __sync_cmpxchg(volatile void *ptr,
					    unsigned long old,
					    unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__("lock; cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__("lock; cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__("lock; cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

static inline unsigned long __cmpxchg_local(volatile void *ptr,
			unsigned long old, unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__("cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__("cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__("cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

#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 = __cmpxchg((ptr), (unsigned long)(o),		\
					(unsigned long)(n), sizeof(*(ptr))); \
	else								\
		__ret = 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 = __cmpxchg_local((ptr), (unsigned long)(o),	\
					(unsigned long)(n), sizeof(*(ptr))); \
	else								\
		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
					(unsigned long)(n), sizeof(*(ptr))); \
	__ret;								\
})
#endif

static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
				      unsigned long long new)
{
	unsigned long long prev;
	__asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
			     : "=A"(prev)
			     : "b"((unsigned long)new),
			       "c"((unsigned long)(new >> 32)),
			       "m"(*__xg(ptr)),
			       "0"(old)
			     : "memory");
	return prev;
}

static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
			unsigned long long old, unsigned long long new)
{
	unsigned long long prev;
	__asm__ __volatile__("cmpxchg8b %3"
			     : "=A"(prev)
			     : "b"((unsigned long)new),
			       "c"((unsigned long)(new >> 32)),
			       "m"(*__xg(ptr)),
			       "0"(old)
			     : "memory");
	return prev;
}

#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