summaryrefslogtreecommitdiff
path: root/arch/x86/include/asm/spinlock.h
blob: bf156ded74b56006a76cc02b8917984117af8afd (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
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
#ifndef _ASM_X86_SPINLOCK_H
#define _ASM_X86_SPINLOCK_H

#include <linux/jump_label.h>
#include <linux/atomic.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
#include <asm/paravirt.h>
#include <asm/bitops.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.
 *
 * These are fair FIFO ticket locks, which support up to 2^16 CPUs.
 *
 * (the type definitions are in asm/spinlock_types.h)
 */

#ifdef CONFIG_X86_32
# define LOCK_PTR_REG "a"
#else
# define LOCK_PTR_REG "D"
#endif

#if defined(CONFIG_X86_32) && \
	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
/*
 * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
 * (PPro errata 66, 92)
 */
# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
#else
# define UNLOCK_LOCK_PREFIX
#endif

/* How long a lock should spin before we consider blocking */
#define SPIN_THRESHOLD	(1 << 15)

extern struct static_key paravirt_ticketlocks_enabled;
static __always_inline bool static_key_false(struct static_key *key);

#ifdef CONFIG_PARAVIRT_SPINLOCKS

static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
{
	set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
}

#else  /* !CONFIG_PARAVIRT_SPINLOCKS */
static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock,
							__ticket_t ticket)
{
}
static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
							__ticket_t ticket)
{
}

#endif /* CONFIG_PARAVIRT_SPINLOCKS */

static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
	return lock.tickets.head == lock.tickets.tail;
}

/*
 * Ticket locks are conceptually two parts, one indicating the current head of
 * the queue, and the other indicating the current tail. The lock is acquired
 * by atomically noting the tail and incrementing it by one (thus adding
 * ourself to the queue and noting our position), then waiting until the head
 * becomes equal to the the initial value of the tail.
 *
 * We use an xadd covering *both* parts of the lock, to increment the tail and
 * also load the position of the head, which takes care of memory ordering
 * issues and should be optimal for the uncontended case. Note the tail must be
 * in the high part, because a wide xadd increment of the low part would carry
 * up and contaminate the high part.
 */
static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
{
	register struct __raw_tickets inc = { .tail = TICKET_LOCK_INC };

	inc = xadd(&lock->tickets, inc);
	if (likely(inc.head == inc.tail))
		goto out;

	inc.tail &= ~TICKET_SLOWPATH_FLAG;
	for (;;) {
		unsigned count = SPIN_THRESHOLD;

		do {
			if (ACCESS_ONCE(lock->tickets.head) == inc.tail)
				goto out;
			cpu_relax();
		} while (--count);
		__ticket_lock_spinning(lock, inc.tail);
	}
out:	barrier();	/* make sure nothing creeps before the lock is taken */
}

static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	arch_spinlock_t old, new;

	old.tickets = ACCESS_ONCE(lock->tickets);
	if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
		return 0;

	new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);

	/* cmpxchg is a full barrier, so nothing can move before it */
	return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
}

static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
					    arch_spinlock_t old)
{
	arch_spinlock_t new;

	BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);

	/* Perform the unlock on the "before" copy */
	old.tickets.head += TICKET_LOCK_INC;

	/* Clear the slowpath flag */
	new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);

	/*
	 * If the lock is uncontended, clear the flag - use cmpxchg in
	 * case it changes behind our back though.
	 */
	if (new.tickets.head != new.tickets.tail ||
	    cmpxchg(&lock->head_tail, old.head_tail,
					new.head_tail) != old.head_tail) {
		/*
		 * Lock still has someone queued for it, so wake up an
		 * appropriate waiter.
		 */
		__ticket_unlock_kick(lock, old.tickets.head);
	}
}

static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	if (TICKET_SLOWPATH_FLAG &&
	    static_key_false(&paravirt_ticketlocks_enabled)) {
		arch_spinlock_t prev;

		prev = *lock;
		add_smp(&lock->tickets.head, TICKET_LOCK_INC);

		/* add_smp() is a full mb() */

		if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
			__ticket_unlock_slowpath(lock, prev);
	} else
		__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
}

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);

	return tmp.tail != tmp.head;
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);

	return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
}
#define arch_spin_is_contended	arch_spin_is_contended

static __always_inline void arch_spin_lock_flags(arch_spinlock_t *lock,
						  unsigned long flags)
{
	arch_spin_lock(lock);
}

static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
	while (arch_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.
 */

/**
 * read_can_lock - would read_trylock() succeed?
 * @lock: the rwlock in question.
 */
static inline int arch_read_can_lock(arch_rwlock_t *lock)
{
	return lock->lock > 0;
}

/**
 * write_can_lock - would write_trylock() succeed?
 * @lock: the rwlock in question.
 */
static inline int arch_write_can_lock(arch_rwlock_t *lock)
{
	return lock->write == WRITE_LOCK_CMP;
}

static inline void arch_read_lock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(dec) " (%0)\n\t"
		     "jns 1f\n"
		     "call __read_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (rw) : "memory");
}

static inline void arch_write_lock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX WRITE_LOCK_SUB(%1) "(%0)\n\t"
		     "jz 1f\n"
		     "call __write_lock_failed\n\t"
		     "1:\n"
		     ::LOCK_PTR_REG (&rw->write), "i" (RW_LOCK_BIAS)
		     : "memory");
}

static inline int arch_read_trylock(arch_rwlock_t *lock)
{
	READ_LOCK_ATOMIC(t) *count = (READ_LOCK_ATOMIC(t) *)lock;

	if (READ_LOCK_ATOMIC(dec_return)(count) >= 0)
		return 1;
	READ_LOCK_ATOMIC(inc)(count);
	return 0;
}

static inline int arch_write_trylock(arch_rwlock_t *lock)
{
	atomic_t *count = (atomic_t *)&lock->write;

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

static inline void arch_read_unlock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX READ_LOCK_SIZE(inc) " %0"
		     :"+m" (rw->lock) : : "memory");
}

static inline void arch_write_unlock(arch_rwlock_t *rw)
{
	asm volatile(LOCK_PREFIX WRITE_LOCK_ADD(%1) "%0"
		     : "+m" (rw->write) : "i" (RW_LOCK_BIAS) : "memory");
}

#define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
#define arch_write_lock_flags(lock, flags) arch_write_lock(lock)

#undef READ_LOCK_SIZE
#undef READ_LOCK_ATOMIC
#undef WRITE_LOCK_ADD
#undef WRITE_LOCK_SUB
#undef WRITE_LOCK_CMP

#define arch_spin_relax(lock)	cpu_relax()
#define arch_read_relax(lock)	cpu_relax()
#define arch_write_relax(lock)	cpu_relax()

#endif /* _ASM_X86_SPINLOCK_H */