linux/arch/x86/include/asm/spinlock.h

#ifndef _ASM_X86_SPINLOCK_H
#define _ASM_X86_SPINLOCK_H

#include <linux/atomic.h>
#include <asm/page.h>
#include <asm/processor.h>
#include <linux/compiler.h>
#include <asm/paravirt.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 are currently limited to 256
 * CPUs.
 *
 * (the type definitions are in asm/spinlock_types.h)
 */

#ifdef CONFIG_X86_32
# define LOCK_PTR_REG "a"
# define REG_PTR_MODE "k"
#else
# define LOCK_PTR_REG "D"
# define REG_PTR_MODE "q"
#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

/*
 * 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.
 *
 * With fewer than 2^8 possible CPUs, we can use x86's partial registers to
 * save some instructions and make the code more elegant. There really isn't
 * much between them in performance though, especially as locks are out of line.
 */
#if (NR_CPUS < 256)
static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
{
	register union {
		struct __raw_tickets tickets;
		unsigned short slock;
	} inc = { .slock = 1 << TICKET_SHIFT };

	asm volatile (LOCK_PREFIX "xaddw %w0, %1\n"
		      : "+Q" (inc), "+m" (lock->slock) : : "memory", "cc");

	for (;;) {
		if (inc.tickets.head == inc.tickets.tail)
			break;
		cpu_relax();
		inc.tickets.head = ACCESS_ONCE(lock->tickets.head);
	}
	barrier();		/* make sure nothing creeps before the lock is taken */
}

static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
{
	unsigned int tmp, new;

	asm volatile("movzwl %2, %0\n\t"
		     "cmpb %h0,%b0\n\t"
		     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
		     "jne 1f\n\t"
		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
		     "1:"
		     "sete %b1\n\t"
		     "movzbl %b1,%0\n\t"
		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
		     :
		     : "memory", "cc");

	return tmp;
}

static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
{
	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
		     : "+m" (lock->slock)
		     :
		     : "memory", "cc");
}
#else
static __always_inline void __ticket_spin_lock(arch_spinlock_t *lock)
{
	unsigned inc = 1 << TICKET_SHIFT;
	__ticket_t tmp;

	asm volatile(LOCK_PREFIX "xaddl %0, %1\n\t"
		     : "+r" (inc), "+m" (lock->slock)
		     : : "memory", "cc");

	tmp = inc;
	inc >>= TICKET_SHIFT;

	for (;;) {
		if ((__ticket_t)inc == tmp)
			break;
		cpu_relax();
		tmp = ACCESS_ONCE(lock->tickets.head);
	}
	barrier();		/* make sure nothing creeps before the lock is taken */
}

static __always_inline int __ticket_spin_trylock(arch_spinlock_t *lock)
{
	unsigned tmp;
	unsigned new;

	asm volatile("movl %2,%0\n\t"
		     "movl %0,%1\n\t"
		     "roll $16, %0\n\t"
		     "cmpl %0,%1\n\t"
		     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
		     "jne 1f\n\t"
		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
		     "1:"
		     "sete %b1\n\t"
		     "movzbl %b1,%0\n\t"
		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
		     :
		     : "memory", "cc");

	return tmp;
}

static __always_inline void __ticket_spin_unlock(arch_spinlock_t *lock)
{
	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
		     : "+m" (lock->slock)
		     :
		     : "memory", "cc");
}
#endif

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

	return !!(tmp.tail ^ tmp.head);
}

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

	return ((tmp.tail - tmp.head) & TICKET_MASK) > 1;
}

#ifndef CONFIG_PARAVIRT_SPINLOCKS

static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
	return __ticket_spin_is_locked(lock);
}

static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
	return __ticket_spin_is_contended(lock);
}
#define arch_spin_is_contended	arch_spin_is_contended

static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
{
	__ticket_spin_lock(lock);
}

static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
{
	return __ticket_spin_trylock(lock);
}

static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
	__ticket_spin_unlock(lock);
}

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

#endif	/* CONFIG_PARAVIRT_SPINLOCKS */

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()

/* The {read|write|spin}_lock() on x86 are full memory barriers. */
static inline void smp_mb__after_lock(void) { }
#define ARCH_HAS_SMP_MB_AFTER_LOCK

#endif /* _ASM_X86_SPINLOCK_H */