summaryrefslogtreecommitdiffstats
path: root/arch/sparc/include/asm/cmpxchg_64.h
blob: 4028f4f1e5612b4717b87b0943920d6e95d69e86 (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
/* 64-bit atomic xchg() and cmpxchg() definitions.
 *
 * Copyright (C) 1996, 1997, 2000 David S. Miller (davem@redhat.com)
 */

#ifndef __ARCH_SPARC64_CMPXCHG__
#define __ARCH_SPARC64_CMPXCHG__

static inline unsigned long
__cmpxchg_u32(volatile int *m, int old, int new)
{
	__asm__ __volatile__("cas [%2], %3, %0"
			     : "=&r" (new)
			     : "0" (new), "r" (m), "r" (old)
			     : "memory");

	return new;
}

static inline unsigned long xchg32(__volatile__ unsigned int *m, unsigned int val)
{
	unsigned long tmp1, tmp2;

	__asm__ __volatile__(
"	mov		%0, %1\n"
"1:	lduw		[%4], %2\n"
"	cas		[%4], %2, %0\n"
"	cmp		%2, %0\n"
"	bne,a,pn	%%icc, 1b\n"
"	 mov		%1, %0\n"
	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
	: "0" (val), "r" (m)
	: "cc", "memory");
	return val;
}

static inline unsigned long xchg64(__volatile__ unsigned long *m, unsigned long val)
{
	unsigned long tmp1, tmp2;

	__asm__ __volatile__(
"	mov		%0, %1\n"
"1:	ldx		[%4], %2\n"
"	casx		[%4], %2, %0\n"
"	cmp		%2, %0\n"
"	bne,a,pn	%%xcc, 1b\n"
"	 mov		%1, %0\n"
	: "=&r" (val), "=&r" (tmp1), "=&r" (tmp2)
	: "0" (val), "r" (m)
	: "cc", "memory");
	return val;
}

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

void __xchg_called_with_bad_pointer(void);

/*
 * Use 4 byte cas instruction to achieve 2 byte xchg. Main logic
 * here is to get the bit shift of the byte we are interested in.
 * The XOR is handy for reversing the bits for big-endian byte order.
 */
static inline unsigned long
xchg16(__volatile__ unsigned short *m, unsigned short val)
{
	unsigned long maddr = (unsigned long)m;
	int bit_shift = (((unsigned long)m & 2) ^ 2) << 3;
	unsigned int mask = 0xffff << bit_shift;
	unsigned int *ptr = (unsigned int  *) (maddr & ~2);
	unsigned int old32, new32, load32;

	/* Read the old value */
	load32 = *ptr;

	do {
		old32 = load32;
		new32 = (load32 & (~mask)) | val << bit_shift;
		load32 = __cmpxchg_u32(ptr, old32, new32);
	} while (load32 != old32);

	return (load32 & mask) >> bit_shift;
}

static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
				       int size)
{
	switch (size) {
	case 2:
		return xchg16(ptr, x);
	case 4:
		return xchg32(ptr, x);
	case 8:
		return xchg64(ptr, x);
	}
	__xchg_called_with_bad_pointer();
	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.
 */

#include <asm-generic/cmpxchg-local.h>


static inline unsigned long
__cmpxchg_u64(volatile long *m, unsigned long old, unsigned long new)
{
	__asm__ __volatile__("casx [%2], %3, %0"
			     : "=&r" (new)
			     : "0" (new), "r" (m), "r" (old)
			     : "memory");

	return new;
}

/*
 * Use 4 byte cas instruction to achieve 1 byte cmpxchg. Main logic
 * here is to get the bit shift of the byte we are interested in.
 * The XOR is handy for reversing the bits for big-endian byte order
 */
static inline unsigned long
__cmpxchg_u8(volatile unsigned char *m, unsigned char old, unsigned char new)
{
	unsigned long maddr = (unsigned long)m;
	int bit_shift = (((unsigned long)m & 3) ^ 3) << 3;
	unsigned int mask = 0xff << bit_shift;
	unsigned int *ptr = (unsigned int *) (maddr & ~3);
	unsigned int old32, new32, load;
	unsigned int load32 = *ptr;

	do {
		new32 = (load32 & ~mask) | (new << bit_shift);
		old32 = (load32 & ~mask) | (old << bit_shift);
		load32 = __cmpxchg_u32(ptr, old32, new32);
		if (load32 == old32)
			return old;
		load = (load32 & mask) >> bit_shift;
	} while (load == old);

	return load;
}

/* This function doesn't exist, so you'll get a linker error
   if something tries to do an invalid cmpxchg().  */
void __cmpxchg_called_with_bad_pointer(void);

static inline unsigned long
__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new, int size)
{
	switch (size) {
		case 1:
			return __cmpxchg_u8(ptr, old, new);
		case 4:
			return __cmpxchg_u32(ptr, old, new);
		case 8:
			return __cmpxchg_u64(ptr, old, new);
	}
	__cmpxchg_called_with_bad_pointer();
	return old;
}

#define cmpxchg(ptr,o,n)						 \
  ({									 \
     __typeof__(*(ptr)) _o_ = (o);					 \
     __typeof__(*(ptr)) _n_ = (n);					 \
     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
				    (unsigned long)_n_, sizeof(*(ptr))); \
  })

/*
 * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
 * them available.
 */

static inline unsigned long __cmpxchg_local(volatile void *ptr,
				      unsigned long old,
				      unsigned long new, int size)
{
	switch (size) {
	case 4:
	case 8:	return __cmpxchg(ptr, old, new, size);
	default:
		return __cmpxchg_local_generic(ptr, old, new, size);
	}

	return old;
}

#define cmpxchg_local(ptr, o, n)				  	\
	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
			(unsigned long)(n), sizeof(*(ptr))))
#define cmpxchg64_local(ptr, o, n)					\
  ({									\
	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
	cmpxchg_local((ptr), (o), (n));					\
  })
#define cmpxchg64(ptr, o, n)	cmpxchg64_local((ptr), (o), (n))

#endif /* __ARCH_SPARC64_CMPXCHG__ */