aboutsummaryrefslogtreecommitdiff
path: root/include/asm-x86/spinlock.h
blob: afd4b80ff0ad3f442d87362ebfcbaff6df7ddd8a (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
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
#ifndef _X86_SPINLOCK_H_
#define _X86_SPINLOCK_H_

#include <asm/atomic.h>
#include <asm/rwlock.h>
#include <asm/page.h>
#include <asm/processor.h>

/*
 * Your basic SMP spinlocks, allowing only a single CPU anywhere
 *
 * Simple spin lock operations.  There are two variants, one clears IRQ's
 * on the local processor, one does not.
 *
 * We make no fairness assumptions. They have a cost.
 *
 * (the type definitions are in asm/spinlock_types.h)
 */

#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else
#define CLI_STRING	"cli"
#define STI_STRING	"sti"
#define CLI_STI_CLOBBERS
#define CLI_STI_INPUT_ARGS
#endif /* CONFIG_PARAVIRT */

#ifdef CONFIG_X86_32
typedef char _slock_t;
# define LOCK_INS_DEC "decb"
# define LOCK_INS_XCH "xchgb"
# define LOCK_INS_MOV "movb"
# define LOCK_INS_CMP "cmpb"
# define LOCK_PTR_REG "a"
#else
typedef int _slock_t;
# define LOCK_INS_DEC "decl"
# define LOCK_INS_XCH "xchgl"
# define LOCK_INS_MOV "movl"
# define LOCK_INS_CMP "cmpl"
# define LOCK_PTR_REG "D"
#endif

static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
{
	return *(volatile _slock_t *)(&(lock)->slock) <= 0;
}

static inline void __raw_spin_lock(raw_spinlock_t *lock)
{
	asm volatile(
		"\n1:\t"
		LOCK_PREFIX " ; " LOCK_INS_DEC " %0\n\t"
		"jns 3f\n"
		"2:\t"
		"rep;nop\n\t"
		LOCK_INS_CMP " $0,%0\n\t"
		"jle 2b\n\t"
		"jmp 1b\n"
		"3:\n\t"
		: "+m" (lock->slock) : : "memory");
}

/*
 * It is easier for the lock validator if interrupts are not re-enabled
 * in the middle of a lock-acquire. This is a performance feature anyway
 * so we turn it off:
 *
 * NOTE: there's an irqs-on section here, which normally would have to be
 * irq-traced, but on CONFIG_TRACE_IRQFLAGS we never use this variant.
 */
#ifndef CONFIG_PROVE_LOCKING
static inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
					 unsigned long flags)
{
	asm volatile(
		"\n1:\t"
		LOCK_PREFIX " ; " LOCK_INS_DEC " %[slock]\n\t"
		"jns 5f\n"
		"testl $0x200, %[flags]\n\t"
		"jz 4f\n\t"
		STI_STRING "\n"
		"3:\t"
		"rep;nop\n\t"
		LOCK_INS_CMP " $0, %[slock]\n\t"
		"jle 3b\n\t"
		CLI_STRING "\n\t"
		"jmp 1b\n"
		"4:\t"
		"rep;nop\n\t"
		LOCK_INS_CMP " $0, %[slock]\n\t"
		"jg 1b\n\t"
		"jmp 4b\n"
		"5:\n\t"
		: [slock] "+m" (lock->slock)
		: [flags] "r" ((u32)flags)
		  CLI_STI_INPUT_ARGS
		: "memory" CLI_STI_CLOBBERS);
}
#endif

static inline int __raw_spin_trylock(raw_spinlock_t *lock)
{
	_slock_t oldval;

	asm volatile(
		LOCK_INS_XCH " %0,%1"
		:"=q" (oldval), "+m" (lock->slock)
		:"0" (0) : "memory");

	return oldval > 0;
}

/*
 * __raw_spin_unlock based on writing $1 to the low byte.
 * This method works. Despite all the confusion.
 * (except on PPro SMP or if we are using OOSTORE, so we use xchgb there)
 * (PPro errata 66, 92)
 */
#if defined(X86_64) || \
	(!defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE))

static inline void __raw_spin_unlock(raw_spinlock_t *lock)
{
	asm volatile(LOCK_INS_MOV " $1,%0" : "=m" (lock->slock) :: "memory");
}

#else

static inline void __raw_spin_unlock(raw_spinlock_t *lock)
{
	unsigned char oldval = 1;

	asm volatile("xchgb %b0, %1"
		     : "=q" (oldval), "+m" (lock->slock)
		     : "0" (oldval) : "memory");
}

#endif

static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
{
	while (__raw_spin_is_locked(lock))
		cpu_relax();
}

/*
 * Read-write spinlocks, allowing multiple readers
 * but only one writer.
 *
 * NOTE! it is quite common to have readers in interrupts
 * but no interrupt writers. For those circumstances we
 * can "mix" irq-safe locks - any writer needs to get a
 * irq-safe write-lock, but readers can get non-irqsafe
 * read-locks.
 *
 * On x86, we implement read-write locks as a 32-bit counter
 * with the high bit (sign) being the "contended" bit.
 */

static inline int __raw_read_can_lock(raw_rwlock_t *lock)
{
	return (int)(lock)->lock > 0;
}

static inline int __raw_write_can_lock(raw_rwlock_t *lock)
{
	return (lock)->lock == RW_LOCK_BIAS;
}

static inline void __raw_read_lock(raw_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
		     "jns 1f\n"
		     "call __read_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (rw) : "memory");
}

static inline void __raw_write_lock(raw_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t"
		     "jz 1f\n"
		     "call __write_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory");
}

static inline int __raw_read_trylock(raw_rwlock_t *lock)
{
	atomic_t *count = (atomic_t *)lock;

	atomic_dec(count);
	if (atomic_read(count) >= 0)
		return 1;
	atomic_inc(count);
	return 0;
}

static inline int __raw_write_trylock(raw_rwlock_t *lock)
{
	atomic_t *count = (atomic_t *)lock;

	if (atomic_sub_and_test(RW_LOCK_BIAS, count))
		return 1;
	atomic_add(RW_LOCK_BIAS, count);
	return 0;
}

static inline void __raw_read_unlock(raw_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
}

static inline void __raw_write_unlock(raw_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX "addl %1, %0"
		     : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
}

#define _raw_spin_relax(lock)	cpu_relax()
#define _raw_read_relax(lock)	cpu_relax()
#define _raw_write_relax(lock)	cpu_relax()

#endif